SlideShare a Scribd company logo
1 of 19
Building ADAS
SYSTEM from scratch
Alex Myakov, Chief CV Advocate
Yury Gorbachev, CV Integration & Optimization lead
September, 2016
Who we are ?
Itseez was acquired by IoTG/Intel in July, 2016
Itseez was founded in 2005:
• 3 ex- Intel co-Founders + 1 Principal Engineer
• OpenCV development and support (2005-present)
• OpenVX initiative leaders: v1.0 and v1.1 were published in
October, 2014 and in May, 2016
SW Products: ADAS, Facense, AcceleratedCV (ACV)
Skills: CV algorithms, HW specific optimization, 3+
years of deep learning (DL)
Industries: automotive, security, robotics, wearables,etc
Building ADAS System from Scratch
The Dream and Ambition:
• Create state-of-the-art software based front
camera ADAS algos
• License such algos to Tier-1s and OEMs
Starting point (late 2013):
• Strong knowledge of CV
• Strong knowledge of embedded/optimization
• Good knowledge of cameras/sensors/optics
• No ADAS/automotive specific knowledge
Building ADAS solution from scratch
Strategy:
• Highly portable CV algos (pure ARM optimized code)
• Open SW platform (Android, Linux)
• Simplest system possible
• Cheapest COTS components
• Camera (optics, sensor, packaging)
• HW platform
• Easy/fast installation in any car with no dependence
on car parameters
• Automatic or simple calibration
ADAS Project Timeline
2013
• TSR
• Demo platform:
Nexus 4
2014
• +LDW
• +FCW
• Demo Platform:
Asus Transformer
Tablet + Android OS
+ Standalone
Camera
2015
• +PD
• Demo Platform:
TK1+ Linux OS +
Standalone Camera
• Demos with QNX:
• CES 2015
• TU Update 2015
2016
• PoCs:
• +Semantic Road
Segmentation
• +Obstacle Detection
• +Driver Monitoring
• Demos with QNX:
• CES 2016
Demo Setup
Camera:
• 1M
• 1280H x 800V
• HDR/WDR
• 30 fps
Embedded
Platform
USB 3.0
Snap-and-go concept:
• Simple and fast installation in any car
• No dependence on car parameters
• Automatic calibration or simple
calibration
Lessons Learned
We expected ADAS to be just another CV application !
• we ended up running into and solving lots of issues
• SW development/testing paradigm
• HW issues
• Datasets
ADAS Solution SW Architecture
TSR LDW FCW PD
Common Image Processing Pipeline + Autocalibration
OpenCV
IPP AcceleratedCV (ACV)
x86 ARM
CV algo prototyping on desktop
Lab testing/CI on server
Execution on target
Live test/benchmarking
SW design approach
ADAS algorithms are purely software based:
• Possible to design and test on desktops
• Purely based on OpenCV
• No special software skills are required (GPU, DSP,
etc)
• Flexible and upgradable
Solved platform compatibility issues
• No vendor provides cross-platform CV framework
• OpenCV is limited in supporting this
Created AcceleratedCV (ACV) library to address
platform compatibility issue
Continuous integration
Any change in ADAS algorithms or processing
pipeline requires complete re-evaluation
• Detection/processing quality on the entire dataset
• Performance figures for each ADAS algorithm
Benefits from pure SW based approach
• Quality evaluation on servers/cloud for entire dataset
• Performance benchmarking on multiple HW targets
• Reduces test time from days to hours!
Datasets
CV algorithms require datasets for design and
testing:
• No available commercial datasets
• Research datasets cannot be used for products
Our own datasets for each ADAS algo were created:
• Different conditions (rain, snow, sun)
• Geographical locations
• Dataset annotation and management tools
• Many days of driving + many months of annotation
The market offering of quality annotated datasets is
still very limited !
Datasets stats
TSR: 2.5K good unique signs
PD: 83K+ pedestrian bounding boxes
FCW: 5K+ different cars and ca 1K trucks
LDW: 0.5M+ boundaries
HW Issues
HW issues are caused by consumer “gradeness” of
components
Temperature issues:
• Camera overheating -> skipped or corrupted frames
• HW platform overheating -> throttling
System issues:
• throttling and unpredicted system behavior under
heavy processing loads
Mechanical issues:
• USB 3.0 cable connectors get loose and break
Where is Deep Learning in our algos?
Original ADAS algos were based on classical CV
• Embedded platforms were too weak and not able to
provide required performance Gflops
• Datasets were too small to yield quality DL results
• DL technology was not fully there
Conventional CV + small DL networks:
• PD: validation of PD results based on classical CV –
increase DR and reduce FA rate
• Driver monitoring: conventional face detector + DL
based headpose estimation
Semantic Road Segmentation - PoC
Obstacle Detection using SfM - PoC
•We estimate 3D coordinates using
points tracking and vehicle speed.
•Obstacles are calculated as
clusters of points above the road
plane.
Semantic segmentation + Obstacle Detection
Deep Learning - Silver Bullet ?
• Great new CV tool
• Large datasets
• A few orders of magnitude more compute
than classic CV
• FuSa implications
Questions ?
Contact Details:
Alex Myakov, Chief CV Advocate
Email: alex.myakov@intel.com

More Related Content

What's hot

What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...
What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...
What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...Embitel Technologies (I) PVT LTD
 
System on chip buses
System on chip busesSystem on chip buses
System on chip busesA B Shinde
 
4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognitionNgaire Taylor
 
Most Media Oriented System Transport
Most Media Oriented System TransportMost Media Oriented System Transport
Most Media Oriented System TransportPruthvi Monarch
 
Real Time System Validation using Hardware in Loop (HIL) Digital Platform
Real Time System Validation using Hardware in Loop (HIL) Digital PlatformReal Time System Validation using Hardware in Loop (HIL) Digital Platform
Real Time System Validation using Hardware in Loop (HIL) Digital PlatformSHIMI S L
 
SRAM read and write and sense amplifier
SRAM read and write and sense amplifierSRAM read and write and sense amplifier
SRAM read and write and sense amplifierSoumyajit Langal
 
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...MaxEye Technologies Private Limited
 
Controller area network -ppt
Controller area network -pptController area network -ppt
Controller area network -pptvelichetiphani
 
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan K
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan KController Area Network (CAN) Protocol || Automotive Electronics || Hariharan K
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan KHariharan Krishnan
 
In‐Vehicle Networking: a Survey and Look Forward
In‐Vehicle Networking: a Survey and Look ForwardIn‐Vehicle Networking: a Survey and Look Forward
In‐Vehicle Networking: a Survey and Look ForwardRealTime-at-Work (RTaW)
 
Controller Area Network (Basic Level Presentation)
Controller Area Network (Basic Level Presentation)Controller Area Network (Basic Level Presentation)
Controller Area Network (Basic Level Presentation)Vikas Kumar
 
The Basics of Automotive Ethernet Webinar Slidedeck
The Basics of Automotive Ethernet Webinar SlidedeckThe Basics of Automotive Ethernet Webinar Slidedeck
The Basics of Automotive Ethernet Webinar Slidedeckteledynelecroy
 
Autosar software component
Autosar software componentAutosar software component
Autosar software componentFarzad Sadeghi
 
Soc architecture and design
Soc architecture and designSoc architecture and design
Soc architecture and designSatya Harish
 

What's hot (20)

V2X, V2I, and the Cellular Infrastructure
V2X, V2I, and the Cellular InfrastructureV2X, V2I, and the Cellular Infrastructure
V2X, V2I, and the Cellular Infrastructure
 
What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...
What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...
What is Diagnostic over Internet Protocol (DoIP) and How it Supports Remote V...
 
System on chip buses
System on chip busesSystem on chip buses
System on chip buses
 
4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition
 
CAN Bus
CAN BusCAN Bus
CAN Bus
 
Most Media Oriented System Transport
Most Media Oriented System TransportMost Media Oriented System Transport
Most Media Oriented System Transport
 
Real Time System Validation using Hardware in Loop (HIL) Digital Platform
Real Time System Validation using Hardware in Loop (HIL) Digital PlatformReal Time System Validation using Hardware in Loop (HIL) Digital Platform
Real Time System Validation using Hardware in Loop (HIL) Digital Platform
 
Face recognisation system
Face recognisation systemFace recognisation system
Face recognisation system
 
SRAM read and write and sense amplifier
SRAM read and write and sense amplifierSRAM read and write and sense amplifier
SRAM read and write and sense amplifier
 
Sram pdf
Sram pdfSram pdf
Sram pdf
 
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...
Automotive Infotainment Test Solution or In-Vehicle Infotainment Testing (IVI...
 
Controller area network -ppt
Controller area network -pptController area network -ppt
Controller area network -ppt
 
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan K
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan KController Area Network (CAN) Protocol || Automotive Electronics || Hariharan K
Controller Area Network (CAN) Protocol || Automotive Electronics || Hariharan K
 
Embedded Systems in Automotive
Embedded Systems in Automotive Embedded Systems in Automotive
Embedded Systems in Automotive
 
In‐Vehicle Networking: a Survey and Look Forward
In‐Vehicle Networking: a Survey and Look ForwardIn‐Vehicle Networking: a Survey and Look Forward
In‐Vehicle Networking: a Survey and Look Forward
 
Controller Area Network (Basic Level Presentation)
Controller Area Network (Basic Level Presentation)Controller Area Network (Basic Level Presentation)
Controller Area Network (Basic Level Presentation)
 
The Basics of Automotive Ethernet Webinar Slidedeck
The Basics of Automotive Ethernet Webinar SlidedeckThe Basics of Automotive Ethernet Webinar Slidedeck
The Basics of Automotive Ethernet Webinar Slidedeck
 
Autosar software component
Autosar software componentAutosar software component
Autosar software component
 
Soc architecture and design
Soc architecture and designSoc architecture and design
Soc architecture and design
 
Lin protocol
Lin protocolLin protocol
Lin protocol
 

Viewers also liked

The flex ray protocol
The flex ray protocolThe flex ray protocol
The flex ray protocolWissam Kafa
 
flexray technology in modern cars
flexray technology in modern carsflexray technology in modern cars
flexray technology in modern carsAmit Yerva
 
FPGA Design with Python and MyHDL
FPGA Design with Python and MyHDLFPGA Design with Python and MyHDL
FPGA Design with Python and MyHDLGuy Eschemann
 
Altera Cyclone IV FPGA Customer Presentation
Altera Cyclone IV FPGA Customer PresentationAltera Cyclone IV FPGA Customer Presentation
Altera Cyclone IV FPGA Customer PresentationAltera Corporation
 
Configuring the communication on FlexRay: the case of the static segment
Configuring the communication on FlexRay: the case of the static segmentConfiguring the communication on FlexRay: the case of the static segment
Configuring the communication on FlexRay: the case of the static segmentNicolas Navet
 
20 Inspiring Quotes From William Zinsser's "On Writing Well"
20 Inspiring Quotes From William Zinsser's "On Writing Well"20 Inspiring Quotes From William Zinsser's "On Writing Well"
20 Inspiring Quotes From William Zinsser's "On Writing Well"Glenn Leibowitz
 
Crevativty & innovation ppt mba
Crevativty & innovation ppt  mbaCrevativty & innovation ppt  mba
Crevativty & innovation ppt mbaBabasab Patil
 
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...J. Skyler Fernandes
 

Viewers also liked (12)

The flex ray protocol
The flex ray protocolThe flex ray protocol
The flex ray protocol
 
flexray technology in modern cars
flexray technology in modern carsflexray technology in modern cars
flexray technology in modern cars
 
FPGA Design with Python and MyHDL
FPGA Design with Python and MyHDLFPGA Design with Python and MyHDL
FPGA Design with Python and MyHDL
 
Altera Cyclone IV FPGA Customer Presentation
Altera Cyclone IV FPGA Customer PresentationAltera Cyclone IV FPGA Customer Presentation
Altera Cyclone IV FPGA Customer Presentation
 
Advanced Driver Assistance System using FPGA
Advanced Driver Assistance System using FPGAAdvanced Driver Assistance System using FPGA
Advanced Driver Assistance System using FPGA
 
Flexray
FlexrayFlexray
Flexray
 
FlexRay
FlexRayFlexRay
FlexRay
 
Configuring the communication on FlexRay: the case of the static segment
Configuring the communication on FlexRay: the case of the static segmentConfiguring the communication on FlexRay: the case of the static segment
Configuring the communication on FlexRay: the case of the static segment
 
RTL Presentation by Pr. John Connor
RTL Presentation by Pr. John ConnorRTL Presentation by Pr. John Connor
RTL Presentation by Pr. John Connor
 
20 Inspiring Quotes From William Zinsser's "On Writing Well"
20 Inspiring Quotes From William Zinsser's "On Writing Well"20 Inspiring Quotes From William Zinsser's "On Writing Well"
20 Inspiring Quotes From William Zinsser's "On Writing Well"
 
Crevativty & innovation ppt mba
Crevativty & innovation ppt  mbaCrevativty & innovation ppt  mba
Crevativty & innovation ppt mba
 
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...
The Best Startup Investor Pitch Deck & How to Present to Angels & Venture Cap...
 

Similar to Building ADAS system from scratch

GoPoint Technology Business Overview
GoPoint Technology Business OverviewGoPoint Technology Business Overview
GoPoint Technology Business Overviewbrennanhamilton
 
Functional verification techniques EW16 session
Functional verification techniques  EW16 sessionFunctional verification techniques  EW16 session
Functional verification techniques EW16 sessionSameh El-Ashry
 
Webinar on Latency and throughput computation of automotive EE network
Webinar on Latency and throughput computation of automotive EE networkWebinar on Latency and throughput computation of automotive EE network
Webinar on Latency and throughput computation of automotive EE networkDeepak Shankar
 
Software defined vehicles,automotive standards (safety, security), agile cont...
Software defined vehicles,automotive standards (safety, security), agile cont...Software defined vehicles,automotive standards (safety, security), agile cont...
Software defined vehicles,automotive standards (safety, security), agile cont...Dr. Anish Cheriyan (PhD)
 
AWS Certified DevOps Engineer: What it is and how to get certified
AWS Certified DevOps Engineer: What it is and how to get certifiedAWS Certified DevOps Engineer: What it is and how to get certified
AWS Certified DevOps Engineer: What it is and how to get certifiedInfosec
 
Serverless Computing: Driving Innovation and Business Value
Serverless Computing: Driving Innovation and Business ValueServerless Computing: Driving Innovation and Business Value
Serverless Computing: Driving Innovation and Business ValueAlibaba Cloud
 
Optimization of computer vision algorithms in codesign methodologies
Optimization of computer vision algorithms in codesign methodologiesOptimization of computer vision algorithms in codesign methodologies
Optimization of computer vision algorithms in codesign methodologiesMarcos Nieto
 
System Architecture Exploration Training Class
System Architecture Exploration Training ClassSystem Architecture Exploration Training Class
System Architecture Exploration Training ClassDeepak Shankar
 
CSC AWS re:Invent Enterprise DevOps session
CSC AWS re:Invent Enterprise DevOps sessionCSC AWS re:Invent Enterprise DevOps session
CSC AWS re:Invent Enterprise DevOps sessionTom Laszewski
 
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...Amazon Web Services
 
Introduction to architecture exploration
Introduction to architecture explorationIntroduction to architecture exploration
Introduction to architecture explorationDeepak Shankar
 
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...Ed Sattar
 
Lads Tech Company Profile V4.0
Lads Tech Company Profile V4.0Lads Tech Company Profile V4.0
Lads Tech Company Profile V4.0Resident Meer
 
Arun kumar Dharmalingam[3y_10m].pdf
Arun kumar Dharmalingam[3y_10m].pdfArun kumar Dharmalingam[3y_10m].pdf
Arun kumar Dharmalingam[3y_10m].pdfRajSingh616745
 
Directions NA Choosing the best possible Azure platform for NAV
Directions NA Choosing the best possible Azure platform for NAVDirections NA Choosing the best possible Azure platform for NAV
Directions NA Choosing the best possible Azure platform for NAVAleksandar Totovic
 
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation..."Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...Edge AI and Vision Alliance
 

Similar to Building ADAS system from scratch (20)

GoPoint Technology Business Overview
GoPoint Technology Business OverviewGoPoint Technology Business Overview
GoPoint Technology Business Overview
 
Functional verification techniques EW16 session
Functional verification techniques  EW16 sessionFunctional verification techniques  EW16 session
Functional verification techniques EW16 session
 
Webinar on Latency and throughput computation of automotive EE network
Webinar on Latency and throughput computation of automotive EE networkWebinar on Latency and throughput computation of automotive EE network
Webinar on Latency and throughput computation of automotive EE network
 
Software defined vehicles,automotive standards (safety, security), agile cont...
Software defined vehicles,automotive standards (safety, security), agile cont...Software defined vehicles,automotive standards (safety, security), agile cont...
Software defined vehicles,automotive standards (safety, security), agile cont...
 
AWS Certified DevOps Engineer: What it is and how to get certified
AWS Certified DevOps Engineer: What it is and how to get certifiedAWS Certified DevOps Engineer: What it is and how to get certified
AWS Certified DevOps Engineer: What it is and how to get certified
 
Serverless Computing: Driving Innovation and Business Value
Serverless Computing: Driving Innovation and Business ValueServerless Computing: Driving Innovation and Business Value
Serverless Computing: Driving Innovation and Business Value
 
Optimization of computer vision algorithms in codesign methodologies
Optimization of computer vision algorithms in codesign methodologiesOptimization of computer vision algorithms in codesign methodologies
Optimization of computer vision algorithms in codesign methodologies
 
System Architecture Exploration Training Class
System Architecture Exploration Training ClassSystem Architecture Exploration Training Class
System Architecture Exploration Training Class
 
CSC AWS re:Invent Enterprise DevOps session
CSC AWS re:Invent Enterprise DevOps sessionCSC AWS re:Invent Enterprise DevOps session
CSC AWS re:Invent Enterprise DevOps session
 
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...
(ENT210) Accelerating Business Innovation with DevOps on AWS | AWS re:Invent ...
 
Introduction to architecture exploration
Introduction to architecture explorationIntroduction to architecture exploration
Introduction to architecture exploration
 
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...
Cloud Based Cognitive Learning & IT Project Performance Platform (CLIPP Platf...
 
RSI GmbH - Intro
RSI GmbH - IntroRSI GmbH - Intro
RSI GmbH - Intro
 
Code or No Code
Code or No CodeCode or No Code
Code or No Code
 
AdnanAlbujuq_2
AdnanAlbujuq_2AdnanAlbujuq_2
AdnanAlbujuq_2
 
Lads Tech Company Profile V4.0
Lads Tech Company Profile V4.0Lads Tech Company Profile V4.0
Lads Tech Company Profile V4.0
 
Arun kumar Dharmalingam[3y_10m].pdf
Arun kumar Dharmalingam[3y_10m].pdfArun kumar Dharmalingam[3y_10m].pdf
Arun kumar Dharmalingam[3y_10m].pdf
 
Webinar on RISC-V
Webinar on RISC-VWebinar on RISC-V
Webinar on RISC-V
 
Directions NA Choosing the best possible Azure platform for NAV
Directions NA Choosing the best possible Azure platform for NAVDirections NA Choosing the best possible Azure platform for NAV
Directions NA Choosing the best possible Azure platform for NAV
 
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation..."Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
 

More from Yury Gorbachev

How to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitHow to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitYury Gorbachev
 
Develop and optimize CV/DL applications with Intel OpenVINO toolkit
Develop and optimize CV/DL applications with Intel OpenVINO toolkitDevelop and optimize CV/DL applications with Intel OpenVINO toolkit
Develop and optimize CV/DL applications with Intel OpenVINO toolkitYury Gorbachev
 
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™Yury Gorbachev
 
Real-world Vision Systems Design: Challenges and Techniques
Real-world Vision Systems Design: Challenges and TechniquesReal-world Vision Systems Design: Challenges and Techniques
Real-world Vision Systems Design: Challenges and TechniquesYury Gorbachev
 
OpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedOpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedYury Gorbachev
 

More from Yury Gorbachev (6)

How to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitHow to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO Toolkit
 
Develop and optimize CV/DL applications with Intel OpenVINO toolkit
Develop and optimize CV/DL applications with Intel OpenVINO toolkitDevelop and optimize CV/DL applications with Intel OpenVINO toolkit
Develop and optimize CV/DL applications with Intel OpenVINO toolkit
 
OpenVINO introduction
OpenVINO introductionOpenVINO introduction
OpenVINO introduction
 
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™
Enabling Cross-platform Deep Learning Applications with Intel OpenVINO™
 
Real-world Vision Systems Design: Challenges and Techniques
Real-world Vision Systems Design: Challenges and TechniquesReal-world Vision Systems Design: Challenges and Techniques
Real-world Vision Systems Design: Challenges and Techniques
 
OpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedOpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons Learned
 

Recently uploaded

CRM Contender Series: HubSpot vs. Salesforce
CRM Contender Series: HubSpot vs. SalesforceCRM Contender Series: HubSpot vs. Salesforce
CRM Contender Series: HubSpot vs. SalesforceBrainSell Technologies
 
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfInnovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfYashikaSharma391629
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Velvetech LLC
 
Salesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZSalesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZABSYZ Inc
 
Unveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesUnveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesŁukasz Chruściel
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Mater
 
Introduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfIntroduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfFerryKemperman
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalLionel Briand
 
Post Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on IdentityPost Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on Identityteam-WIBU
 
英国UN学位证,北安普顿大学毕业证书1:1制作
英国UN学位证,北安普顿大学毕业证书1:1制作英国UN学位证,北安普顿大学毕业证书1:1制作
英国UN学位证,北安普顿大学毕业证书1:1制作qr0udbr0
 
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...Akihiro Suda
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Developmentvyaparkranti
 
A healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfA healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfMarharyta Nedzelska
 
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxUI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxAndreas Kunz
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesPhilip Schwarz
 
How To Manage Restaurant Staff -BTRESTRO
How To Manage Restaurant Staff -BTRESTROHow To Manage Restaurant Staff -BTRESTRO
How To Manage Restaurant Staff -BTRESTROmotivationalword821
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureDinusha Kumarasiri
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...confluent
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...Technogeeks
 

Recently uploaded (20)

CRM Contender Series: HubSpot vs. Salesforce
CRM Contender Series: HubSpot vs. SalesforceCRM Contender Series: HubSpot vs. Salesforce
CRM Contender Series: HubSpot vs. Salesforce
 
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfInnovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...
 
Salesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZSalesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZ
 
Unveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesUnveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New Features
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)
 
Introduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdfIntroduction Computer Science - Software Design.pdf
Introduction Computer Science - Software Design.pdf
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive Goal
 
Post Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on IdentityPost Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on Identity
 
英国UN学位证,北安普顿大学毕业证书1:1制作
英国UN学位证,北安普顿大学毕业证书1:1制作英国UN学位证,北安普顿大学毕业证书1:1制作
英国UN学位证,北安普顿大学毕业证书1:1制作
 
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Development
 
A healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfA healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdf
 
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptxUI5ers live - Custom Controls wrapping 3rd-party libs.pptx
UI5ers live - Custom Controls wrapping 3rd-party libs.pptx
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a series
 
How To Manage Restaurant Staff -BTRESTRO
How To Manage Restaurant Staff -BTRESTROHow To Manage Restaurant Staff -BTRESTRO
How To Manage Restaurant Staff -BTRESTRO
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with Azure
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...
 

Building ADAS system from scratch

  • 1. Building ADAS SYSTEM from scratch Alex Myakov, Chief CV Advocate Yury Gorbachev, CV Integration & Optimization lead September, 2016
  • 2. Who we are ? Itseez was acquired by IoTG/Intel in July, 2016 Itseez was founded in 2005: • 3 ex- Intel co-Founders + 1 Principal Engineer • OpenCV development and support (2005-present) • OpenVX initiative leaders: v1.0 and v1.1 were published in October, 2014 and in May, 2016 SW Products: ADAS, Facense, AcceleratedCV (ACV) Skills: CV algorithms, HW specific optimization, 3+ years of deep learning (DL) Industries: automotive, security, robotics, wearables,etc
  • 3. Building ADAS System from Scratch The Dream and Ambition: • Create state-of-the-art software based front camera ADAS algos • License such algos to Tier-1s and OEMs Starting point (late 2013): • Strong knowledge of CV • Strong knowledge of embedded/optimization • Good knowledge of cameras/sensors/optics • No ADAS/automotive specific knowledge
  • 4. Building ADAS solution from scratch Strategy: • Highly portable CV algos (pure ARM optimized code) • Open SW platform (Android, Linux) • Simplest system possible • Cheapest COTS components • Camera (optics, sensor, packaging) • HW platform • Easy/fast installation in any car with no dependence on car parameters • Automatic or simple calibration
  • 5. ADAS Project Timeline 2013 • TSR • Demo platform: Nexus 4 2014 • +LDW • +FCW • Demo Platform: Asus Transformer Tablet + Android OS + Standalone Camera 2015 • +PD • Demo Platform: TK1+ Linux OS + Standalone Camera • Demos with QNX: • CES 2015 • TU Update 2015 2016 • PoCs: • +Semantic Road Segmentation • +Obstacle Detection • +Driver Monitoring • Demos with QNX: • CES 2016
  • 6. Demo Setup Camera: • 1M • 1280H x 800V • HDR/WDR • 30 fps Embedded Platform USB 3.0 Snap-and-go concept: • Simple and fast installation in any car • No dependence on car parameters • Automatic calibration or simple calibration
  • 7. Lessons Learned We expected ADAS to be just another CV application ! • we ended up running into and solving lots of issues • SW development/testing paradigm • HW issues • Datasets
  • 8. ADAS Solution SW Architecture TSR LDW FCW PD Common Image Processing Pipeline + Autocalibration OpenCV IPP AcceleratedCV (ACV) x86 ARM CV algo prototyping on desktop Lab testing/CI on server Execution on target Live test/benchmarking
  • 9. SW design approach ADAS algorithms are purely software based: • Possible to design and test on desktops • Purely based on OpenCV • No special software skills are required (GPU, DSP, etc) • Flexible and upgradable Solved platform compatibility issues • No vendor provides cross-platform CV framework • OpenCV is limited in supporting this Created AcceleratedCV (ACV) library to address platform compatibility issue
  • 10. Continuous integration Any change in ADAS algorithms or processing pipeline requires complete re-evaluation • Detection/processing quality on the entire dataset • Performance figures for each ADAS algorithm Benefits from pure SW based approach • Quality evaluation on servers/cloud for entire dataset • Performance benchmarking on multiple HW targets • Reduces test time from days to hours!
  • 11. Datasets CV algorithms require datasets for design and testing: • No available commercial datasets • Research datasets cannot be used for products Our own datasets for each ADAS algo were created: • Different conditions (rain, snow, sun) • Geographical locations • Dataset annotation and management tools • Many days of driving + many months of annotation The market offering of quality annotated datasets is still very limited !
  • 12. Datasets stats TSR: 2.5K good unique signs PD: 83K+ pedestrian bounding boxes FCW: 5K+ different cars and ca 1K trucks LDW: 0.5M+ boundaries
  • 13. HW Issues HW issues are caused by consumer “gradeness” of components Temperature issues: • Camera overheating -> skipped or corrupted frames • HW platform overheating -> throttling System issues: • throttling and unpredicted system behavior under heavy processing loads Mechanical issues: • USB 3.0 cable connectors get loose and break
  • 14. Where is Deep Learning in our algos? Original ADAS algos were based on classical CV • Embedded platforms were too weak and not able to provide required performance Gflops • Datasets were too small to yield quality DL results • DL technology was not fully there Conventional CV + small DL networks: • PD: validation of PD results based on classical CV – increase DR and reduce FA rate • Driver monitoring: conventional face detector + DL based headpose estimation
  • 16. Obstacle Detection using SfM - PoC •We estimate 3D coordinates using points tracking and vehicle speed. •Obstacles are calculated as clusters of points above the road plane.
  • 17. Semantic segmentation + Obstacle Detection
  • 18. Deep Learning - Silver Bullet ? • Great new CV tool • Large datasets • A few orders of magnitude more compute than classic CV • FuSa implications
  • 19. Questions ? Contact Details: Alex Myakov, Chief CV Advocate Email: alex.myakov@intel.com