“Sea-thru: A Method for Removing Water from Underwater Images,” a Presentation from the Harbor Branch Oceanographic Institute
•
0 likes•148 views
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2021/01/sea-thru-a-method-for-removing-water-from-underwater-images-a-presentation-from-the-harbor-branch-oceanographic-institute/ Derya Akkaynak, Engineer and Oceanographer at the Harbor Branch Oceanographic Institute, presents the “Sea-thru: A Method for Removing Water from Underwater Images” tutorial at the September 2020 Embedded Vision Summit. Very large underwater image datasets are generated every day that capture important information regarding the state of our oceans, but they cannot be efficiently analyzed with powerful computer vision and machine learning algorithms because water degrades images too severely for automated analysis. Existing methods that attempt to restore lost colors and contrast perform poorly and, as a result, the analysis of most underwater imagery requires costly manual effort, affecting the pace at which marine science moves forward. In this presentation, Akkaynak shows that a fundamental reason for this poor performance is the common use of an atmospheric image formation model for the ocean. Based on the (more) physically accurate underwater image formation model recently proposed and validated, she then introduces the Sea-thru algorithm that successfully removes water from underwater images in a rapid, objective, and repeatable way, creating exciting opportunities for the future of underwater exploration and conservation.
Report
Share
Report
Share
Download to read offline
Recommended
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/learning-compact-dnn-models-for-embedded-vision-a-presentation-from-the-university-of-maryland-at-college-park/
Shuvra Bhattacharyya, Professor at the University of Maryland at College Park, presents the “Learning Compact DNN Models for Embedded Vision” tutorial at the May 2023 Embedded Vision Summit.
In this talk, Bhattacharyya explores methods to transform large deep neural network (DNN) models into effective compact models. The transformation process that he focuses on—from large to compact DNN form—is referred to as pruning. Pruning involves the removal of neurons or parameters from a neural network. When performed strategically, pruning can lead to significant reductions in computational complexity without significant degradation in accuracy. It is sometimes even possible to increase accuracy through pruning.
Pruning provides a general approach for facilitating real-time inference in resource-constrained embedded computer vision systems. Bhattacharyya provides an overview of important aspects to consider when applying or developing a DNN pruning method and presents details on a recently introduced pruning method called NeuroGRS. NeuroGRS considers structures and trained weights jointly throughout the pruning process and can result in significantly more compact models compared to other pruning methods.“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/introduction-to-computer-vision-with-cnns-a-presentation-from-mohammad-haghighat/
Independent consultant Mohammad Haghighat presents the “Introduction to Computer Vision with Convolutional Neural Networks” tutorial at the May 2023 Embedded Vision Summit.
This presentation covers the basics of computer vision using convolutional neural networks. Haghighat begins by introducing some important conventional computer vision techniques and then transition to explaining the basics of machine learning and convolutional neural networks (CNNs) and showing how CNNs are used in visual perception.
Haghighat illustrates the building blocks and computational elements of neural networks through examples. This session provides an overview of how modern computer vision algorithms are designed, trained and used in real-world applications.“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/selecting-tools-for-developing-monitoring-and-maintaining-ml-models-a-presentation-from-yummly/
Parshad Patel, Data Scientist at Yummly, presents the “Selecting Tools for Developing, Monitoring and Maintaining ML Models” tutorial at the May 2023 Embedded Vision Summit.
With the boom in tools for developing, monitoring and maintaining ML models, data science teams have many options to choose from. Proprietary tools provided by cloud service providers are enticing, but teams may fear being locked in—and may worry that these tools are too costly or missing important features when compared with alternatives from specialized providers.
Fortunately, most proprietary, fee-based tools have an open-source component that can be integrated into a home-grown solution at low cost. This can be a good starting point, enabling teams to get started with modern tools without making big investments and leaving the door open to evolve tool selection over time. In this talk, Patel presents a step-by-step process for creating an MLOps tool set that enables you to deliver maximum value as a data scientist. He shares how Yummly built pipelines for model development and put them into production using open-source projects.“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/building-accelerated-gstreamer-applications-for-video-and-audio-ai-a-presentation-from-wave-spectrum/
Abdo Babukr, Accelerated Computing Consultant at Wave Spectrum, presents the “Building Accelerated GStreamer Applications for Video and Audio AI,” tutorial at the May 2023 Embedded Vision Summit.
GStreamer is a popular open-source framework for creating streaming media applications. Developers often use GStreamer to streamline the development of computer vision and audio perception applications. Since perceptual algorithms are often quite demanding in terms of processing performance, in many cases developers need to find ways to accelerate key GStreamer building blocks, taking advantage of specialized features of their target processor or co-processor.
In this talk, Babukr introduces GStreamer and shows how to use it to build computer vision and audio perception applications. He also shows how to create efficient, high-performance GStreamer applications that utilize specialized hardware features.“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/understanding-selecting-and-optimizing-object-detectors-for-edge-applications-a-presentation-from-walmart-global-tech/
Md Nasir Uddin Laskar, Staff Machine Learning Engineer at Walmart Global Tech, presents the “Understanding, Selecting and Optimizing Object Detectors for Edge Applications” tutorial at the May 2023 Embedded Vision Summit.
Object detectors count objects in a scene and determine their precise locations, while also labeling them. Object detection plays a crucial role in many vision applications, from autonomous driving to smart appliances. In many of these applications, it’s necessary or desirable to implement object detection at the edge.
In this presentation, Laskar explores the evolution of object detection algorithms, from traditional approaches to deep learning-based methods and transformer-based architectures. He delves into widely used approaches for object detection, such as two-stage R-CNNs and one-stage YOLO algorithms, and examines their strengths and weaknesses. And he provides guidance on how to evaluate and select an object detector for an edge application.“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/introduction-to-modern-lidar-for-machine-perception-a-presentation-from-the-university-of-ottawa/
Robert Laganière, Professor at the University of Ottawa and CEO of Sensor Cortek, presents the “Introduction to Modern LiDAR for Machine Perception” tutorial at the May 2023 Embedded Vision Summit.
In this presentation, Laganière provides an introduction to light detection and ranging (LiDAR) technology. He explains how LiDAR sensors work and their main advantages and disadvantages. He also introduces different approaches to LiDAR, including scanning and flash LiDAR.
Laganière explores the types of data produced by LiDAR sensors and explains how this data can be processed using deep neural networks. He also examines the synergy between LiDAR and cameras, and the concept of pseudo-LiDAR for detection.“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
Recommended
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/learning-compact-dnn-models-for-embedded-vision-a-presentation-from-the-university-of-maryland-at-college-park/
Shuvra Bhattacharyya, Professor at the University of Maryland at College Park, presents the “Learning Compact DNN Models for Embedded Vision” tutorial at the May 2023 Embedded Vision Summit.
In this talk, Bhattacharyya explores methods to transform large deep neural network (DNN) models into effective compact models. The transformation process that he focuses on—from large to compact DNN form—is referred to as pruning. Pruning involves the removal of neurons or parameters from a neural network. When performed strategically, pruning can lead to significant reductions in computational complexity without significant degradation in accuracy. It is sometimes even possible to increase accuracy through pruning.
Pruning provides a general approach for facilitating real-time inference in resource-constrained embedded computer vision systems. Bhattacharyya provides an overview of important aspects to consider when applying or developing a DNN pruning method and presents details on a recently introduced pruning method called NeuroGRS. NeuroGRS considers structures and trained weights jointly throughout the pruning process and can result in significantly more compact models compared to other pruning methods.“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/introduction-to-computer-vision-with-cnns-a-presentation-from-mohammad-haghighat/
Independent consultant Mohammad Haghighat presents the “Introduction to Computer Vision with Convolutional Neural Networks” tutorial at the May 2023 Embedded Vision Summit.
This presentation covers the basics of computer vision using convolutional neural networks. Haghighat begins by introducing some important conventional computer vision techniques and then transition to explaining the basics of machine learning and convolutional neural networks (CNNs) and showing how CNNs are used in visual perception.
Haghighat illustrates the building blocks and computational elements of neural networks through examples. This session provides an overview of how modern computer vision algorithms are designed, trained and used in real-world applications.“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/selecting-tools-for-developing-monitoring-and-maintaining-ml-models-a-presentation-from-yummly/
Parshad Patel, Data Scientist at Yummly, presents the “Selecting Tools for Developing, Monitoring and Maintaining ML Models” tutorial at the May 2023 Embedded Vision Summit.
With the boom in tools for developing, monitoring and maintaining ML models, data science teams have many options to choose from. Proprietary tools provided by cloud service providers are enticing, but teams may fear being locked in—and may worry that these tools are too costly or missing important features when compared with alternatives from specialized providers.
Fortunately, most proprietary, fee-based tools have an open-source component that can be integrated into a home-grown solution at low cost. This can be a good starting point, enabling teams to get started with modern tools without making big investments and leaving the door open to evolve tool selection over time. In this talk, Patel presents a step-by-step process for creating an MLOps tool set that enables you to deliver maximum value as a data scientist. He shares how Yummly built pipelines for model development and put them into production using open-source projects.“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/building-accelerated-gstreamer-applications-for-video-and-audio-ai-a-presentation-from-wave-spectrum/
Abdo Babukr, Accelerated Computing Consultant at Wave Spectrum, presents the “Building Accelerated GStreamer Applications for Video and Audio AI,” tutorial at the May 2023 Embedded Vision Summit.
GStreamer is a popular open-source framework for creating streaming media applications. Developers often use GStreamer to streamline the development of computer vision and audio perception applications. Since perceptual algorithms are often quite demanding in terms of processing performance, in many cases developers need to find ways to accelerate key GStreamer building blocks, taking advantage of specialized features of their target processor or co-processor.
In this talk, Babukr introduces GStreamer and shows how to use it to build computer vision and audio perception applications. He also shows how to create efficient, high-performance GStreamer applications that utilize specialized hardware features.“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/understanding-selecting-and-optimizing-object-detectors-for-edge-applications-a-presentation-from-walmart-global-tech/
Md Nasir Uddin Laskar, Staff Machine Learning Engineer at Walmart Global Tech, presents the “Understanding, Selecting and Optimizing Object Detectors for Edge Applications” tutorial at the May 2023 Embedded Vision Summit.
Object detectors count objects in a scene and determine their precise locations, while also labeling them. Object detection plays a crucial role in many vision applications, from autonomous driving to smart appliances. In many of these applications, it’s necessary or desirable to implement object detection at the edge.
In this presentation, Laskar explores the evolution of object detection algorithms, from traditional approaches to deep learning-based methods and transformer-based architectures. He delves into widely used approaches for object detection, such as two-stage R-CNNs and one-stage YOLO algorithms, and examines their strengths and weaknesses. And he provides guidance on how to evaluate and select an object detector for an edge application.“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/introduction-to-modern-lidar-for-machine-perception-a-presentation-from-the-university-of-ottawa/
Robert Laganière, Professor at the University of Ottawa and CEO of Sensor Cortek, presents the “Introduction to Modern LiDAR for Machine Perception” tutorial at the May 2023 Embedded Vision Summit.
In this presentation, Laganière provides an introduction to light detection and ranging (LiDAR) technology. He explains how LiDAR sensors work and their main advantages and disadvantages. He also introduces different approaches to LiDAR, including scanning and flash LiDAR.
Laganière explores the types of data produced by LiDAR sensors and explains how this data can be processed using deep neural networks. He also examines the synergy between LiDAR and cameras, and the concept of pseudo-LiDAR for detection.“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/vision-language-representations-for-robotics-a-presentation-from-the-university-of-pennsylvania/
Dinesh Jayaraman, Assistant Professor at the University of Pennsylvania, presents the “Vision-language Representations for Robotics” tutorial at the May 2023 Embedded Vision Summit.
In what format can an AI system best present what it “sees” in a visual scene to help robots accomplish tasks? This question has been a long-standing challenge for computer scientists and robotics engineers. In this presentation, Jayaraman provides insights into cutting-edge techniques being used to help robots better understand their surroundings, learn new skills with minimal guidance and become more capable of performing complex tasks.
Jayaraman discusses recent advances in unsupervised representation learning and explains how these approaches can be used to build visual representations that are appropriate for a controller that decides how the robot should act. In particular, he presents insights from his research group’s recent work on how to represent the constituent objects and entities in a visual scene, and how to combine vision and language in a way that permits effectively translating language-based task descriptions into images depicting the robot’s goals.“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/adas-and-av-sensors-whats-winning-and-why-a-presentation-from-techinsights/
Ian Riches, Vice President of the Global Automotive Practice at TechInsights, presents the “ADAS and AV Sensors: What’s Winning and Why?” tutorial at the May 2023 Embedded Vision Summit.
It’s clear that the number of sensors per vehicle—and the sophistication of these sensors—is growing rapidly, largely thanks to increased adoption of advanced safety and driver assistance features. In this presentation, Riches explores likely future demand for automotive radars, cameras and LiDARs.
Riches examines which vehicle features will drive demand out to 2030, how vehicle architecture change is impacting the market and what sorts of compute platforms these sensors will be connected to. Finally, he shares his firm’s vision of what the landscape could look like far beyond 2030, considering scenarios out to 2050 for automated driving and the resulting sensor demand.“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/computer-vision-in-sports-scalable-solutions-for-downmarkets-a-presentation-from-sportlogiq/
Mehrsan Javan, Co-founder and CTO of Sportlogiq, presents the “Computer Vision in Sports: Scalable Solutions for Downmarket Leagues” tutorial at the May 2023 Embedded Vision Summit.
Sports analytics is about observing, understanding and describing the game in an intelligent manner. In practice, this requires a fully automated, robust end-to-end pipeline, spanning from visual input, to player and group activities, to player and team evaluation to planning. Despite major advancements in computer vision and machine learning, today sports analytics solutions are limited to top leagues and are not widely available for downmarket leagues and youth sports.
In this talk, Javan explains how his company has developed scalable and robust computer vision solutions to democratize sport analytics and offer pro-league-level insights to leagues with modest resources, including youth leagues. He highlights key challenges—such as the requirement for low-cost, low-latency processing and the need for robustness despite variations in venues. He discusses the approaches Sportlogiq tried and how it ultimately overcame these challenges, including the use of transformers and fusion of multiple type of data streams to maximize accuracy.“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/detecting-data-drift-in-image-classification-neural-networks-a-presentation-from-southern-illinois-university/
Spyros Tragoudas, Professor and School Director at Southern Illinois University Carbondale, presents the “Detecting Data Drift in Image Classification Neural Networks” tutorial at the May 2023 Embedded Vision Summit.
An unforeseen change in the input data is called “drift,” and may impact the accuracy of machine learning models. In this talk, Tragoudas presents a novel scheme for diagnosing data drift in the input streams of image classification neural networks. His proposed method for drift detection and quantification uses a threshold dictionary for the prediction probabilities of each class in the neural network model.
The method is applicable to any drift type in images such as noise and weather effects, among others. Tragoudas shares experimental results on various data sets, drift types and neural network models to show that his proposed method estimates the drift magnitude with high accuracy, especially when the level of drift significantly impacts the model’s performance.“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/deep-neural-network-training-diagnosing-problems-and-implementing-solutions-a-presentation-from-sensor-cortek/
Fahed Hassanat, Chief Operating Officer and Head of Engineering at Sensor Cortek, presents the “Deep Neural Network Training: Diagnosing Problems and Implementing Solutions” tutorial at the May 2023 Embedded Vision Summit.
In this presentation, Hassanat delves into some of the most common problems that arise when training deep neural networks. He provides a brief overview of essential training metrics, including accuracy, precision, false positives, false negatives and F1 score.
Hassanat then explores training challenges that arise from problems with hyperparameters, inappropriately sized models, inadequate models, poor-quality datasets, imbalances within training datasets and mismatches between training and testing datasets. To help detect and diagnose training problems, he also covers techniques such as understanding performance curves, recognizing overfitting and underfitting, analyzing confusion matrices and identifying class interaction issues.
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/ai-start-ups-the-perils-of-fishing-for-whales-war-stories-from-the-entrepreneurial-front-lines-a-presentation-from-seechange-technologies/
Tim Hartley, Vice President of Product for SeeChange Technologies, presents the “AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepreneurial Front Lines)” tutorial at the May 2023 Embedded Vision Summit.
You have a killer idea that will change the world. You’ve thought through product-market fit and differentiation. You have seed funding and a world-beating team. Best of all, you’ve caught the attention of major players in your industry. You’ve reached peak “start-up”—that point of limitless possibility—when you go to bed with the same level of energy and enthusiasm you had when you woke. And then the first proof of concept starts…
In this talk, Hartley lays out some of the pitfalls that await those building the next big thing. Using real examples, he shares some of the dos and don’ts, particularly when dealing with that big potential first customer. Hartley discusses the importance of end-to-end design, ensuring your product solves real-world problems. He explores how far the big companies will tell you to jump—and then jump again—for free. And, most importantly, how to build long-term partnerships with major corporations without relying on over-promising sales pitches.“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/a-computer-vision-system-for-autonomous-satellite-maneuvering-a-presentation-from-scout-space/
Andrew Harris, Spacecraft Systems Engineer at SCOUT Space, presents the “Developing a Computer Vision System for Autonomous Satellite Maneuvering” tutorial at the May 2023 Embedded Vision Summit.
Computer vision systems for mobile autonomous machines experience a wide variety of real-world conditions and inputs that can be challenging to capture accurately in training datasets. Few autonomous systems experience more challenging conditions than those in orbit. In this talk, Harris describes how SCOUT Space has designed and trained satellite vision systems using dynamic and physically informed synthetic image datasets.
Harris describes how his company generates synthetic data for this challenging environment and how it leverages new real-world data to improve our datasets. In particular, he explains how these synthetic datasets account for and can replicate real sources of noise and error in the orbital environment, and how his company supplements them with in-space data from the first SCOUT-Vision system, which has been in orbit since 2021.“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/bias-in-computer-vision-its-bigger-than-facial-recognition-a-presentation-from-santa-clara-university/
Susan Kennedy, Assistant Professor of Philosophy at Santa Clara University, presents the “Bias in Computer Vision—It’s Bigger Than Facial Recognition!” tutorial at the May 2023 Embedded Vision Summit.
As AI is increasingly integrated into various industries, concerns about its potential to reproduce or exacerbate bias have become widespread. While the use of AI holds the promise of reducing bias, it can also have unintended consequences, particularly in high-stakes computer vision applications such as facial recognition. However, even seemingly low-stakes computer vision applications such as identifying potholes and damaged roads can also present ethical challenges related to bias.
This talk explores how bias in computer vision often poses an ethical challenge, regardless of the stakes involved. Kennedy discusses the limitations of technical solutions aimed at mitigating bias, and why “bias-free” AI may not be achievable. Instead, she focuses on the importance of adopting a “bias-aware” approach to responsible AI design and explores strategies that can be employed to achieve this.“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/sensor-fusion-techniques-for-accurate-perception-of-objects-in-the-environment-a-presentation-from-sanborn-map-company/
Baharak Soltanian, Vice President of Research and Development for the Sanborn Map Company, presents the “Sensor Fusion Techniques for Accurate Perception of Objects in the Environment” tutorial at the May 2023 Embedded Vision Summit.
Increasingly, perceptual AI is being used to enable devices and systems to obtain accurate estimates of object locations, speeds and trajectories. In demanding applications, this is often best done using a heterogeneous combination of sensors (e.g., vision, radar, LiDAR). In this talk, Soltanian introduces techniques for combining data from multiple sensors to obtain accurate information about objects in the environment.
Soltanian briefly introduces the roles played by Kalman filters, particle filters, Bayesian networks and neural networks in this type of fusion. She then examines alternative fusion architectures, such as centralized and decentralized approaches, to better understand the trade-offs associated with different approaches to sensor fusion as used to enhance the ability of machines to understand their environment.“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/combating-bias-in-production-computer-vision-systems-a-presentation-from-red-cell-partners/
Alex Thaman, Chief Architect at Red Cell Partners, presents the “Combating Bias in Production Computer Vision Systems” tutorial at the May 2023 Embedded Vision Summit.
Bias is a critical challenge in predictive and generative AI that involves images of humans. People have a variety of body shapes, skin tones and other features that can be challenging to represent completely in training data. Without attention to bias risks, ML systems have the potential to treat people unfairly, and even to make humans more likely to do so.
In this talk, Thaman examines the ways in which bias can arise in visual AI systems. He shares techniques for detecting bias and strategies for minimizing it in production AI systems.“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/developing-an-embedded-vision-ai-powered-fitness-system-a-presentation-from-peloton-interactive/
Sanjay Nichani, Vice President for Artificial Intelligence and Computer Vision at Peloton Interactive, presents the “Developing an Embedded Vision AI-powered Fitness System” tutorial at the May 2023 Embedded Vision Summit.
The Guide is Peloton’s first strength-training product that runs on a physical device and also the first that uses AI technology. It turns any TV into an interactive personal training studio. Members have access to Peloton’s instructors, who lead classes that use dumbbells and body weight. The Guide uses an innovative combination of hardware, software and user interface; it is one of only a handful of consumer products in this market that use real-time embedded computer vision, and Peloton’s members love it!
In this talk, Nichani shares insights into how the computer vision technology behind the Guide was built. He focuses on data, models and processes. The AI and Computer Vision team at Peloton worked through numerous obstacles by using synthetic data, advanced algorithms and field-testing iteration to create an affordable AI-powered device that enables at-home fitness for everyone.“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/navigating-the-evolving-venture-capital-landscape-for-edge-ai-start-ups-a-presentation-from-hpe-pathfinder/
Todd Poole, Director of Venture Capital Investments for HPE Pathfinder Ventures, presents the “Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups” tutorial at the May 2023 Embedded Vision Summit.
The venture capital environment has undergone a huge shift in the past year. In this talk, Poole explains how the VC landscape has changed and the implications for start-ups. He examines the impacts on valuations, VC’s willingness to fund, appetite for risk and leverage in deal structuring and terms negotiation.
Pool explores how AI and ML hardware and software companies have been affected differently from the broader start-up ecosystem and considers the distinct challenges faced by start-ups in the edge AI sector. He offers guidance for founders, soon-to-be-founders and start-up employees on how to navigate this dynamic environment and strategize effectively in response to changing market conditions.“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/advanced-presence-sensing-what-it-means-for-the-smart-home-a-presentation-from-omdia/
Jack Narcotta, Principal Analyst for the Smart Home at Omdia, presents the “Advanced Presence Sensing: What It Means for the Smart Home” tutorial at the May 2023 Embedded Vision Summit.
Eventually, homes will become highly autonomous—powered by ubiquitous, connected, intelligent devices (sometimes referred to as ambient computing)—but this remains a distant vision. In the meantime, advanced presence sensing innovations from component manufacturers, software developers and smart home device companies are enabling meaningful improvements in convenience, efficiency and safety.
Omdia expects advanced presence detection to be adopted rapidly in the coming years, and to become a key factor in how consumers select devices and service providers. In this talk, Narcotta provides an overview of key enabling technologies, market appetite, consumer expectations and long-term outlook for advanced presence sensing in the home.“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/tracking-and-fusing-diverse-risk-factors-to-drive-a-safer-future-a-presentation-from-nauto/
Yoav Banin, Chief Product and Business Development Officer, and Tahmida Mahmud, Engineering Manager for Perception, both of Nauto, presents the “Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future” tutorial at the May 2023 Embedded Vision Summit.
Unless you’re a gang member or drug addict, driving is your top risk. But which risks can you handle and which can kill you? Since 96% of collisions are caused by human error and 75% are unconscious (the driver is not aware of the risk), Nauto used one billion miles of real-life driving data to find out, feeding it into a model fusing 26 road context, driver action/attention and vehicle dynamics factors to predict collisions, near misses and safe driving.
Nauto, as described by Banin and Mahmud in this presentation, found that drivers can handle most single risks, but multiple simultaneous risks can be deadly. Some combinations are 1,000 times more dangerous than regular driving. Nauto’s “SAFER” model can be fitted to any late-model vehicle. It can be trained with labeled data from historical trips or through reinforcement learning from observations of excellent and poor drivers. A time series matrix can help you see a few seconds into the future.“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/mipi-csi-2-image-sensor-interface-standard-features-enable-efficient-embedded-vision-systems-a-presentation-from-the-mipi-alliance/
Haran Thanigasalam, Camera and Imaging Consultant to the MIPI Alliance, presents the “MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedded Vision Systems” tutorial at the May 2023 Embedded Vision Summit.
As computer vision applications continue to evolve rapidly, there’s a growing need for a smarter standardized interface connecting multiple image sensors to processors for real-time perception and decision-making. In this presentation, Thanigasalam provides a deep dive into the latest version of the widely implemented CSI-2 v4.0 interface from MIPI Alliance.
This new version includes key features specifically designed to support computer vision applications, including democratized Smart Region of Interest, Always-On Sentinel Conduit, Multi-Pixel Compression and Latency Reduction and Transport Efficiency. These novel features enable sophisticated machine awareness with reduced system power and processing needs, making them well suited for consumer, commercial and infrastructure platforms.“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/introduction-to-the-csi-2-image-sensor-interface-standard-a-presentation-from-the-mipi-alliance/
Haran Thanigasalam, Camera and Imaging Consultant to the MIPI Alliance, presents the “Introduction to the MIPI CSI-2 Image Sensor Interface Standard” tutorial at the May 2023 Embedded Vision Summit.
By taking advantage of select features in standardized interfaces, vision system architects can help reduce processor load, cost and power consumption while gaining flexibility to source components from multiple vendors. In this presentation, Thanigasalam introduces the standardized MIPI CSI-2 imaging conduit solution for interfacing image sensors to processors.
Thanigasalam explains how the solution supports basic operations of a camera sensor, including physical frame transport options and orthogonal commands for autoexposure, autofocus, auto white balance and event detection. He also introduces command sets to help bring up and tune sensors. In addition, Thanigasalam explores provisions to alleviate RF emissions, enable aggregation of data from multiple remote sensors and alleviate the need for dual voltage signaling to avoid electrical overstress issues. He also touches on emerging support for frame transport using WiFi.“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/practical-approaches-to-dnn-quantization-a-presentation-from-magic-leap/
Dwith Chenna, Senior Embedded DSP Engineer for Computer Vision at Magic Leap, presents the “Practical Approaches to DNN Quantization” tutorial at the May 2023 Embedded Vision Summit.
Convolutional neural networks, widely used in computer vision tasks, require substantial computation and memory resources, making it challenging to run these models on resource-constrained devices. Quantization involves modifying CNNs to use smaller data types (e.g., switching from 32-bit floating-point values to 8-bit integer values).
Quantization is an effective way to reduce the computation and memory bandwidth requirements of these models, and their memory footprints, making it easier to run them on edge devices. However, quantization does degrade the accuracy of CNNs. In this talk, Chenna surveys practical techniques for CNN quantization and shares best practices, tools and recipes to enable you to get the best results from quantization, including ways to minimize accuracy loss.“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic LeapEdge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/optimizing-image-quality-and-stereo-depth-at-the-edge-a-presentation-from-john-deere/
Travis Davis, Delivery Manager in the Automation and Autonomy Core, and Tarik Loukili, Technical Lead for Automation and Autonomy Applications, both of John Deere, present the “Reinventing Smart Cities with Computer Vision” tutorial at the May 2023 Embedded Vision Summit.
John Deere uses machine learning and computer vision (including stereo vision) for challenging outdoor applications such as obstacle detection, vision-based guidance and weed management, among many others. The quality of the images the company’s systems obtain, and the accuracy of the depth information produced by its stereo cameras, significantly impact the performance of the overall solutions.
In this talk, Davis and Loukili share some of the challenges John Deere has faced in developing image quality improvement and stereo vision algorithms. Many of the techniques found in academic research and prior work cannot be easily implemented in real-time applications at the edge and are difficult to scale for applications with varying performance and cost requirements. They highlight some of the alternative techniques their company has developed to provide optimized image-quality and stereo vision implementations that meet the requirements of John Deere’s product range. Stated another way, they share how they do more with less."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/using-a-collaborative-network-of-distributed-cameras-for-object-tracking-a-presentation-from-invision-ai/
Samuel Örn, Team Lead and Senior Machine Learning and Computer Vision Engineer at Invision AI, presents the “Using a Collaborative Network of Distributed Cameras for Object Tracking” tutorial at the May 2023 Embedded Vision Summit.
Using multiple fixed cameras to track objects requires a careful solution design. To enable scaling the number of cameras, the solution must avoid sending all images across a network. When camera views overlap only a little or not at all, input from multiple cameras must be combined by extending tracking area coverage. When an object can be seen by multiple cameras, this should be used to increase accuracy.
Multiple cameras can better collaborate if they share a common coordinate system; therefore, environment mapping and accurate calibration is necessary. Moreover, the tracking algorithm must scale properly with the number of tracked objects, which can be achieved with a distributed approach. In this talk, Örn covers practical ways of addressing these issues, presents his company’s multiple-camera tracking solution used for vehicle and pedestrian tracking, and shares some of its results.“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...Edge AI and Vision Alliance
More Related Content
More from Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/11/vision-language-representations-for-robotics-a-presentation-from-the-university-of-pennsylvania/
Dinesh Jayaraman, Assistant Professor at the University of Pennsylvania, presents the “Vision-language Representations for Robotics” tutorial at the May 2023 Embedded Vision Summit.
In what format can an AI system best present what it “sees” in a visual scene to help robots accomplish tasks? This question has been a long-standing challenge for computer scientists and robotics engineers. In this presentation, Jayaraman provides insights into cutting-edge techniques being used to help robots better understand their surroundings, learn new skills with minimal guidance and become more capable of performing complex tasks.
Jayaraman discusses recent advances in unsupervised representation learning and explains how these approaches can be used to build visual representations that are appropriate for a controller that decides how the robot should act. In particular, he presents insights from his research group’s recent work on how to represent the constituent objects and entities in a visual scene, and how to combine vision and language in a way that permits effectively translating language-based task descriptions into images depicting the robot’s goals.“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/adas-and-av-sensors-whats-winning-and-why-a-presentation-from-techinsights/
Ian Riches, Vice President of the Global Automotive Practice at TechInsights, presents the “ADAS and AV Sensors: What’s Winning and Why?” tutorial at the May 2023 Embedded Vision Summit.
It’s clear that the number of sensors per vehicle—and the sophistication of these sensors—is growing rapidly, largely thanks to increased adoption of advanced safety and driver assistance features. In this presentation, Riches explores likely future demand for automotive radars, cameras and LiDARs.
Riches examines which vehicle features will drive demand out to 2030, how vehicle architecture change is impacting the market and what sorts of compute platforms these sensors will be connected to. Finally, he shares his firm’s vision of what the landscape could look like far beyond 2030, considering scenarios out to 2050 for automated driving and the resulting sensor demand.“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/computer-vision-in-sports-scalable-solutions-for-downmarkets-a-presentation-from-sportlogiq/
Mehrsan Javan, Co-founder and CTO of Sportlogiq, presents the “Computer Vision in Sports: Scalable Solutions for Downmarket Leagues” tutorial at the May 2023 Embedded Vision Summit.
Sports analytics is about observing, understanding and describing the game in an intelligent manner. In practice, this requires a fully automated, robust end-to-end pipeline, spanning from visual input, to player and group activities, to player and team evaluation to planning. Despite major advancements in computer vision and machine learning, today sports analytics solutions are limited to top leagues and are not widely available for downmarket leagues and youth sports.
In this talk, Javan explains how his company has developed scalable and robust computer vision solutions to democratize sport analytics and offer pro-league-level insights to leagues with modest resources, including youth leagues. He highlights key challenges—such as the requirement for low-cost, low-latency processing and the need for robustness despite variations in venues. He discusses the approaches Sportlogiq tried and how it ultimately overcame these challenges, including the use of transformers and fusion of multiple type of data streams to maximize accuracy.“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/detecting-data-drift-in-image-classification-neural-networks-a-presentation-from-southern-illinois-university/
Spyros Tragoudas, Professor and School Director at Southern Illinois University Carbondale, presents the “Detecting Data Drift in Image Classification Neural Networks” tutorial at the May 2023 Embedded Vision Summit.
An unforeseen change in the input data is called “drift,” and may impact the accuracy of machine learning models. In this talk, Tragoudas presents a novel scheme for diagnosing data drift in the input streams of image classification neural networks. His proposed method for drift detection and quantification uses a threshold dictionary for the prediction probabilities of each class in the neural network model.
The method is applicable to any drift type in images such as noise and weather effects, among others. Tragoudas shares experimental results on various data sets, drift types and neural network models to show that his proposed method estimates the drift magnitude with high accuracy, especially when the level of drift significantly impacts the model’s performance.“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/deep-neural-network-training-diagnosing-problems-and-implementing-solutions-a-presentation-from-sensor-cortek/
Fahed Hassanat, Chief Operating Officer and Head of Engineering at Sensor Cortek, presents the “Deep Neural Network Training: Diagnosing Problems and Implementing Solutions” tutorial at the May 2023 Embedded Vision Summit.
In this presentation, Hassanat delves into some of the most common problems that arise when training deep neural networks. He provides a brief overview of essential training metrics, including accuracy, precision, false positives, false negatives and F1 score.
Hassanat then explores training challenges that arise from problems with hyperparameters, inappropriately sized models, inadequate models, poor-quality datasets, imbalances within training datasets and mismatches between training and testing datasets. To help detect and diagnose training problems, he also covers techniques such as understanding performance curves, recognizing overfitting and underfitting, analyzing confusion matrices and identifying class interaction issues.
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/ai-start-ups-the-perils-of-fishing-for-whales-war-stories-from-the-entrepreneurial-front-lines-a-presentation-from-seechange-technologies/
Tim Hartley, Vice President of Product for SeeChange Technologies, presents the “AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepreneurial Front Lines)” tutorial at the May 2023 Embedded Vision Summit.
You have a killer idea that will change the world. You’ve thought through product-market fit and differentiation. You have seed funding and a world-beating team. Best of all, you’ve caught the attention of major players in your industry. You’ve reached peak “start-up”—that point of limitless possibility—when you go to bed with the same level of energy and enthusiasm you had when you woke. And then the first proof of concept starts…
In this talk, Hartley lays out some of the pitfalls that await those building the next big thing. Using real examples, he shares some of the dos and don’ts, particularly when dealing with that big potential first customer. Hartley discusses the importance of end-to-end design, ensuring your product solves real-world problems. He explores how far the big companies will tell you to jump—and then jump again—for free. And, most importantly, how to build long-term partnerships with major corporations without relying on over-promising sales pitches.“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/a-computer-vision-system-for-autonomous-satellite-maneuvering-a-presentation-from-scout-space/
Andrew Harris, Spacecraft Systems Engineer at SCOUT Space, presents the “Developing a Computer Vision System for Autonomous Satellite Maneuvering” tutorial at the May 2023 Embedded Vision Summit.
Computer vision systems for mobile autonomous machines experience a wide variety of real-world conditions and inputs that can be challenging to capture accurately in training datasets. Few autonomous systems experience more challenging conditions than those in orbit. In this talk, Harris describes how SCOUT Space has designed and trained satellite vision systems using dynamic and physically informed synthetic image datasets.
Harris describes how his company generates synthetic data for this challenging environment and how it leverages new real-world data to improve our datasets. In particular, he explains how these synthetic datasets account for and can replicate real sources of noise and error in the orbital environment, and how his company supplements them with in-space data from the first SCOUT-Vision system, which has been in orbit since 2021.“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/bias-in-computer-vision-its-bigger-than-facial-recognition-a-presentation-from-santa-clara-university/
Susan Kennedy, Assistant Professor of Philosophy at Santa Clara University, presents the “Bias in Computer Vision—It’s Bigger Than Facial Recognition!” tutorial at the May 2023 Embedded Vision Summit.
As AI is increasingly integrated into various industries, concerns about its potential to reproduce or exacerbate bias have become widespread. While the use of AI holds the promise of reducing bias, it can also have unintended consequences, particularly in high-stakes computer vision applications such as facial recognition. However, even seemingly low-stakes computer vision applications such as identifying potholes and damaged roads can also present ethical challenges related to bias.
This talk explores how bias in computer vision often poses an ethical challenge, regardless of the stakes involved. Kennedy discusses the limitations of technical solutions aimed at mitigating bias, and why “bias-free” AI may not be achievable. Instead, she focuses on the importance of adopting a “bias-aware” approach to responsible AI design and explores strategies that can be employed to achieve this.“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/sensor-fusion-techniques-for-accurate-perception-of-objects-in-the-environment-a-presentation-from-sanborn-map-company/
Baharak Soltanian, Vice President of Research and Development for the Sanborn Map Company, presents the “Sensor Fusion Techniques for Accurate Perception of Objects in the Environment” tutorial at the May 2023 Embedded Vision Summit.
Increasingly, perceptual AI is being used to enable devices and systems to obtain accurate estimates of object locations, speeds and trajectories. In demanding applications, this is often best done using a heterogeneous combination of sensors (e.g., vision, radar, LiDAR). In this talk, Soltanian introduces techniques for combining data from multiple sensors to obtain accurate information about objects in the environment.
Soltanian briefly introduces the roles played by Kalman filters, particle filters, Bayesian networks and neural networks in this type of fusion. She then examines alternative fusion architectures, such as centralized and decentralized approaches, to better understand the trade-offs associated with different approaches to sensor fusion as used to enhance the ability of machines to understand their environment.“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/combating-bias-in-production-computer-vision-systems-a-presentation-from-red-cell-partners/
Alex Thaman, Chief Architect at Red Cell Partners, presents the “Combating Bias in Production Computer Vision Systems” tutorial at the May 2023 Embedded Vision Summit.
Bias is a critical challenge in predictive and generative AI that involves images of humans. People have a variety of body shapes, skin tones and other features that can be challenging to represent completely in training data. Without attention to bias risks, ML systems have the potential to treat people unfairly, and even to make humans more likely to do so.
In this talk, Thaman examines the ways in which bias can arise in visual AI systems. He shares techniques for detecting bias and strategies for minimizing it in production AI systems.“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/developing-an-embedded-vision-ai-powered-fitness-system-a-presentation-from-peloton-interactive/
Sanjay Nichani, Vice President for Artificial Intelligence and Computer Vision at Peloton Interactive, presents the “Developing an Embedded Vision AI-powered Fitness System” tutorial at the May 2023 Embedded Vision Summit.
The Guide is Peloton’s first strength-training product that runs on a physical device and also the first that uses AI technology. It turns any TV into an interactive personal training studio. Members have access to Peloton’s instructors, who lead classes that use dumbbells and body weight. The Guide uses an innovative combination of hardware, software and user interface; it is one of only a handful of consumer products in this market that use real-time embedded computer vision, and Peloton’s members love it!
In this talk, Nichani shares insights into how the computer vision technology behind the Guide was built. He focuses on data, models and processes. The AI and Computer Vision team at Peloton worked through numerous obstacles by using synthetic data, advanced algorithms and field-testing iteration to create an affordable AI-powered device that enables at-home fitness for everyone.“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/navigating-the-evolving-venture-capital-landscape-for-edge-ai-start-ups-a-presentation-from-hpe-pathfinder/
Todd Poole, Director of Venture Capital Investments for HPE Pathfinder Ventures, presents the “Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups” tutorial at the May 2023 Embedded Vision Summit.
The venture capital environment has undergone a huge shift in the past year. In this talk, Poole explains how the VC landscape has changed and the implications for start-ups. He examines the impacts on valuations, VC’s willingness to fund, appetite for risk and leverage in deal structuring and terms negotiation.
Pool explores how AI and ML hardware and software companies have been affected differently from the broader start-up ecosystem and considers the distinct challenges faced by start-ups in the edge AI sector. He offers guidance for founders, soon-to-be-founders and start-up employees on how to navigate this dynamic environment and strategize effectively in response to changing market conditions.“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/advanced-presence-sensing-what-it-means-for-the-smart-home-a-presentation-from-omdia/
Jack Narcotta, Principal Analyst for the Smart Home at Omdia, presents the “Advanced Presence Sensing: What It Means for the Smart Home” tutorial at the May 2023 Embedded Vision Summit.
Eventually, homes will become highly autonomous—powered by ubiquitous, connected, intelligent devices (sometimes referred to as ambient computing)—but this remains a distant vision. In the meantime, advanced presence sensing innovations from component manufacturers, software developers and smart home device companies are enabling meaningful improvements in convenience, efficiency and safety.
Omdia expects advanced presence detection to be adopted rapidly in the coming years, and to become a key factor in how consumers select devices and service providers. In this talk, Narcotta provides an overview of key enabling technologies, market appetite, consumer expectations and long-term outlook for advanced presence sensing in the home.“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/tracking-and-fusing-diverse-risk-factors-to-drive-a-safer-future-a-presentation-from-nauto/
Yoav Banin, Chief Product and Business Development Officer, and Tahmida Mahmud, Engineering Manager for Perception, both of Nauto, presents the “Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future” tutorial at the May 2023 Embedded Vision Summit.
Unless you’re a gang member or drug addict, driving is your top risk. But which risks can you handle and which can kill you? Since 96% of collisions are caused by human error and 75% are unconscious (the driver is not aware of the risk), Nauto used one billion miles of real-life driving data to find out, feeding it into a model fusing 26 road context, driver action/attention and vehicle dynamics factors to predict collisions, near misses and safe driving.
Nauto, as described by Banin and Mahmud in this presentation, found that drivers can handle most single risks, but multiple simultaneous risks can be deadly. Some combinations are 1,000 times more dangerous than regular driving. Nauto’s “SAFER” model can be fitted to any late-model vehicle. It can be trained with labeled data from historical trips or through reinforcement learning from observations of excellent and poor drivers. A time series matrix can help you see a few seconds into the future.“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/mipi-csi-2-image-sensor-interface-standard-features-enable-efficient-embedded-vision-systems-a-presentation-from-the-mipi-alliance/
Haran Thanigasalam, Camera and Imaging Consultant to the MIPI Alliance, presents the “MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedded Vision Systems” tutorial at the May 2023 Embedded Vision Summit.
As computer vision applications continue to evolve rapidly, there’s a growing need for a smarter standardized interface connecting multiple image sensors to processors for real-time perception and decision-making. In this presentation, Thanigasalam provides a deep dive into the latest version of the widely implemented CSI-2 v4.0 interface from MIPI Alliance.
This new version includes key features specifically designed to support computer vision applications, including democratized Smart Region of Interest, Always-On Sentinel Conduit, Multi-Pixel Compression and Latency Reduction and Transport Efficiency. These novel features enable sophisticated machine awareness with reduced system power and processing needs, making them well suited for consumer, commercial and infrastructure platforms.“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/introduction-to-the-csi-2-image-sensor-interface-standard-a-presentation-from-the-mipi-alliance/
Haran Thanigasalam, Camera and Imaging Consultant to the MIPI Alliance, presents the “Introduction to the MIPI CSI-2 Image Sensor Interface Standard” tutorial at the May 2023 Embedded Vision Summit.
By taking advantage of select features in standardized interfaces, vision system architects can help reduce processor load, cost and power consumption while gaining flexibility to source components from multiple vendors. In this presentation, Thanigasalam introduces the standardized MIPI CSI-2 imaging conduit solution for interfacing image sensors to processors.
Thanigasalam explains how the solution supports basic operations of a camera sensor, including physical frame transport options and orthogonal commands for autoexposure, autofocus, auto white balance and event detection. He also introduces command sets to help bring up and tune sensors. In addition, Thanigasalam explores provisions to alleviate RF emissions, enable aggregation of data from multiple remote sensors and alleviate the need for dual voltage signaling to avoid electrical overstress issues. He also touches on emerging support for frame transport using WiFi.“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/practical-approaches-to-dnn-quantization-a-presentation-from-magic-leap/
Dwith Chenna, Senior Embedded DSP Engineer for Computer Vision at Magic Leap, presents the “Practical Approaches to DNN Quantization” tutorial at the May 2023 Embedded Vision Summit.
Convolutional neural networks, widely used in computer vision tasks, require substantial computation and memory resources, making it challenging to run these models on resource-constrained devices. Quantization involves modifying CNNs to use smaller data types (e.g., switching from 32-bit floating-point values to 8-bit integer values).
Quantization is an effective way to reduce the computation and memory bandwidth requirements of these models, and their memory footprints, making it easier to run them on edge devices. However, quantization does degrade the accuracy of CNNs. In this talk, Chenna surveys practical techniques for CNN quantization and shares best practices, tools and recipes to enable you to get the best results from quantization, including ways to minimize accuracy loss.“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic LeapEdge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/optimizing-image-quality-and-stereo-depth-at-the-edge-a-presentation-from-john-deere/
Travis Davis, Delivery Manager in the Automation and Autonomy Core, and Tarik Loukili, Technical Lead for Automation and Autonomy Applications, both of John Deere, present the “Reinventing Smart Cities with Computer Vision” tutorial at the May 2023 Embedded Vision Summit.
John Deere uses machine learning and computer vision (including stereo vision) for challenging outdoor applications such as obstacle detection, vision-based guidance and weed management, among many others. The quality of the images the company’s systems obtain, and the accuracy of the depth information produced by its stereo cameras, significantly impact the performance of the overall solutions.
In this talk, Davis and Loukili share some of the challenges John Deere has faced in developing image quality improvement and stereo vision algorithms. Many of the techniques found in academic research and prior work cannot be easily implemented in real-time applications at the edge and are difficult to scale for applications with varying performance and cost requirements. They highlight some of the alternative techniques their company has developed to provide optimized image-quality and stereo vision implementations that meet the requirements of John Deere’s product range. Stated another way, they share how they do more with less."Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2023/10/using-a-collaborative-network-of-distributed-cameras-for-object-tracking-a-presentation-from-invision-ai/
Samuel Örn, Team Lead and Senior Machine Learning and Computer Vision Engineer at Invision AI, presents the “Using a Collaborative Network of Distributed Cameras for Object Tracking” tutorial at the May 2023 Embedded Vision Summit.
Using multiple fixed cameras to track objects requires a careful solution design. To enable scaling the number of cameras, the solution must avoid sending all images across a network. When camera views overlap only a little or not at all, input from multiple cameras must be combined by extending tracking area coverage. When an object can be seen by multiple cameras, this should be used to increase accuracy.
Multiple cameras can better collaborate if they share a common coordinate system; therefore, environment mapping and accurate calibration is necessary. Moreover, the tracking algorithm must scale properly with the number of tracked objects, which can be achieved with a distributed approach. In this talk, Örn covers practical ways of addressing these issues, presents his company’s multiple-camera tracking solution used for vehicle and pedestrian tracking, and shares some of its results.“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...Edge AI and Vision Alliance
More from Edge AI and Vision Alliance (20)
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Introduction to the CSI-2 Image Sensor Interface Standard,” a Presentation f...
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
“Practical Approaches to DNN Quantization,” a Presentation from Magic Leap
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
"Optimizing Image Quality and Stereo Depth at the Edge," a Presentation from ...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
“Using a Collaborative Network of Distributed Cameras for Object Tracking,” a...
Recently uploaded
Recently uploaded (20)
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
“Sea-thru: A Method for Removing Water from Underwater Images,” a Presentation from the Harbor Branch Oceanographic Institute
- 1. © 2020 Your Company Name Sea-thru: A Method for Removing Water From Underwater Images Derya Akkaynak, PhD Harbor Branch Oceanographic Institute September 2020
- 2. © 2020 Your Company Name Sea-thru 2 Derya Akkaynak Tali Treibitz A physics-based computer vision method for color reconstruction of underwater images
- 3. © 2020 Derya Akkaynak Sea-thru: CVPR 2019 3
- 4. © 2020 Derya Akkaynak Sea-thru: CVPR 2019 + CVPR 2018 4
- 5. © 2020 Derya Akkaynak Light Attenuation in Air vs Water 5
- 6. © 2020 Derya Akkaynak 6 Sea-thru: CVPR 2019 + CVPR 2018 + CVPR 2017
- 7. original photo: Matan Yuval Eilat, Israel
- 8. original photo: Derya Akkaynak Papua New Guinea
- 9. original photo: James Rokop Aquastarz Davis,CA
- 10. original photo: Alex Shure Gloucester, MA USA
- 11. © 2020 Derya Akkaynak Sea-thru works for video too! 11 https://youtu.be/oSrBMX8e6yo
- 12. © 2020 Derya Akkaynak Why does Sea-thru work? • It has range as input (RGB-D method) • Does NOT need a color chart (more later) • Does NOT need knowledge of optical water type • Does NOT require forward-facing imaging • First method to use the Akkaynak-Treibitz image formation model (“revised” model) • Derived for the ocean, physically accurate • Rigorously tested & validated underwater • Different coefficients for attenuation and backscatter • Attenuation coefficient NOT a constant per scene 12
- 13. © 2020 Derya Akkaynak Image Formation 13
- 14. © 2020 Derya Akkaynak Image Formation 14 Ic Dc = + Bc - 1 M- 2 M- 3 M- 4 M- 5 M- 6 M- 7 M- 8 M- 9 M- 10 M- 11 M- 12 M- 13 M- 14 M- 15 M- 16 M- 17 M- 18 M- 19 M- 20 M = + image direct signal backscatter
- 15. © 2020 Derya Akkaynak OLD (ATMOSPHERIC) Image Formation Model 15
- 16. © 2020 Derya Akkaynak OLD (ATMOSPHERIC) Image Formation Model 16
- 17. © 2020 Derya Akkaynak Akkaynak-Treibitz Image Formation Model 17 Old Model
- 18. © 2020 Derya Akkaynak Akkaynak-Treibitz Image Formation Model 18
- 19. © 2020 Derya Akkaynak Not just for water! 19
- 20. © 2020 Derya Akkaynak Not just for water! 20
- 21. © 2020 Derya Akkaynak A calibrated experiment 21
- 22. © 2020 Derya Akkaynak Backscatter is a function of range (z) range z(m) Why one color chart is not enough 22 Attenuation coefficient is a function of range (z) range z(m) ** * *
- 23. © 2020 Derya Akkaynak But we rarely have color charts in the scene! 23
- 24. © 2020 Derya Akkaynak Sea-thru in a nutshell 24
- 25. © 2020 Derya Akkaynak Thank you! Derya’s website deryaakkaynak.com/sea-thru Tali’s website http://csms.haifa.ac.il/profiles/tTreibitz/ Papers & data http://csms.haifa.ac.il/profiles/tTreibitz/datas ets/sea_thru/index.html 3D models https://sketchfab.com/Marine_Imaging_Lab 25