its applications. how it works. algorithms, methods

1. Presentation on
Object Tracking
By
Sri Vidhya.K

2.  Introduction to Object tracking
 Applications Of Object tracking
 Object Representation
 Object Detection
 Steps in Object tracking
 Object tracking Algorithm’s
 Methodologies
 Comparison
 Working example of Object tracking in MATLAB
 Conclusion

3.  To track an object over a sequence of
images.
 A method of following an object through
successive image frames to determine its
relative movement with respect to other
objects.

4.  Traffic Information

7.  In a tracking scenario, an object can be defined as
anything that is of interest for further analysis. Objects
can be represented by their shapes. Object shape
representations commonly employed for tracking are:
 Points: The object is represented by a point, that
is, centroid or set of points. Point representation is
suitable for tracking objects that occupy small regions in
an image.
 Primitive geometric shapes: Object shape is
represented by a rectangle, ellipse etc. these are suitable
for representing simple rigid objects and non rigid objects.

9.  Object silhouette and contour: contour
representation defines the boundary of an object.
The region inside the contour is called the
silhouette of the object. These are suitable for
tracking complex non rigid shapes.
 Articulated shape models: These objects are
composed of body parts that are held together
with joints.
 Skeletal models: object skeleton can be
extracted by applying medial axis transform to the
object silhouette. This can be used to model both
articulated and rigid objects.

10.  visual input is usually achieved through digitized images
obtained from a camera connected to a digital computer.
 This camera can be either stationary or moving depending
on the application.
 Beyond image acquisition, the computer performs the
necessary tracking and any higher level tasks using
tracking result.

11.  Every tracking method requires an object detection
mechanism either in every frame or when the object
first appears in the video.
 Challenges of moving object detection:
• Loss of information caused by the 3D world on a 2D
image
• Noise in images
• Complex object motion
• Non-rigid or articulated nature of objects
• Partial or full object occlusions
• Complex object shapes
• Scene illumination changes

13.  Point Tracking: Objects detected in consecutive
frames are represented by points, and the association of
the points is based on the previous object state which
can include object position and motion. This approach
requires an external mechanism to detect the objects in
every frame.
 Kernel Tracking: Kernel refers to the object shape and
appearance
 Silhouette Tracking: Tracking is performed by
estimating the object region in each frame. Silhouette
tracking methods use the information encoded inside
the object region.

14. SEGMENTATION
Foreground /
background extraction
Useful feature
extraction / calculation
Tracking

15. shows the color
image segmentation
result with the edged
image.
show the final
detected
result of joint color
image segmentation
and background
model.
background model

16.  Segmentation is the process of identifying components
of the image. Segmentation involves operations such as
boundary detection, connected component
labeling, thresholding etc. Boundary detection finds out
edges in the image. Thresholding is the process of
reducing the grey levels in the image

17.  As the name suggests this is the process of separating
the foreground and background of the image. Here it is
assumed that foreground contains the objects of interest

18. Background extraction
 Once foreground is extracted a simple subtraction
operation can be used to extract the background.
Following figure illustrates this operation:

19.  Camera model is an important aspect of any object-tracking
algorithm. All the existing objects tracking systems use a
preset camera model. In words camera model is directly
derived from the domain knowledge. Some of the common
camera models are –
1. Single fixed camera
Example: Road traffic tracking system
2. Multiple fixed cameras
Example: Simple surveillance system
3. Single moving camera
Example: Animation and video compression systems
4. Multiple moving cameras
Example: Robot navigation system

21.  Different motion analysis method
◦ SAD of consecutive frames
◦ A threshold is set to detect the moving
The motion
object
is here!

22.  Disadvantage of DMA method
◦ May include covered or covering background
The size of tracking area
is not the same as the size
of tracking object !

23.  Solution: Block-Matching Algorithm (BMA)
◦ Using motion vector to compensate the redundant
part of tracking area
SAD is selected to measure
How two blocks match with
Each other

25. = Image subtraction
D(t)=I(ti) – I(tj)
 Gives an image frame with changed and
unchanged regions
Ideal Case for no motion: I(ti) =
I(tj), D(t)=0

26. Moving
objects
are
detected

27. Methods for Motion Detection
 Frame Differencing
 Background Subtraction
Draw Backs:
 Involves a lot of computations
 Not feasible for DSP implementation

28. Frame1 Frame10
Difference of Two Frames

29. 124 74 32
124 64 18
157 116 184
1 1 0
1 x 0
1 1 1
1 1 0
1 x 0
1 1 1
If (Center pixel < Neighbor
pixel)
Neighbor pixel = 1
Signature Vector11001111
Signature Vector Generation

30. List
Generation
12
8
26 12
5
24
3
87
96 76 43 23
6
12
5
12
8
12
9
23
5
22
9
20
9
22
8
25
1
22
9
22
1
23
4
22
7
22
1
35 58 98
Image
Signatur vector generation
for all pixels
Signature Vectors
1 0 1 1 0 1 0 1
0 0 1 0 1 0 1 1
.
.
.
1 0 1 1 1 0 1 0
List
population
1 0 1 1 0 1 0 1
0 0 1 0 1 0 1 1
.
.
.
1 0 1 1 1 0 1 0Generated List

31. Advantages:
 Compare only two values 0 or 1.
 Similar Illumination Variation for pixel and
neighbouring pixels
Draw Backs:
 As we only deal with only 0`s and 1`s, this
method is sensitive to noise.
 Calculate, store and match process 
computationally Expensive

32. Background
estimation
Frame
differencing
Object
Registration
Method 3: Morphology
Based Object Tracking

33. Background
Estimation
• Image Differencing
• Thresholding
Object
Registration
• Contours are registered
• Width, height and histogram are recorded for each
contour
Frame
Differencing
• Each object represented by a feature vector (the
length, width, area and histogram of the object)

34.  Visual motion pattern of objects and surface in a
scene  by Optical Flow
Frame 1 Frame 2

35.  A method that iteratively shifts a data point to the
average of data points in its neighborhood
Choose a search window
size in the initial
location
Compute the MEAN
location in the
search window
Center the search
window
at the mean
Repeat until
convergence

36. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

37. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

38. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

39. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

40. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

41. Distribution of identical balls
Region of
interest
Center of
mass
Mean Shift
vector
Objective : Find the densest region

42. Distribution of identical balls
Region of
interest
Center of
mass
Objective : Find the densest region

43. KDE Mean Shift
Mean Shift Algorithm
• compute mean shift vector
• translate kernel (window) by mean shift
vector

44. absolute Differences
Easy to implement
Allows continuous
tracking
Computationall
y expensive
Slow and low
accuracy
Census Transform
Immune to noise
and
Illumination
changes
Complex if 
Multiple objects
per frame
Computationall
y expensive
Feature Based
Can track multiple
objects well
Large Memory
consumption
Slow

45. KLT
High accuracy
Less execution time Large memory
MeanShift & CAMShift
Ineffective if
there is heavy
occlusion
Robust to noise and
dynamic scene
Computationally
less expensive

46.  The problem of motion-based object tracking can be
divided into two parts:
 Detecting moving objects in each frame
 Associating the detections corresponding to the same
object over time
 How to detect red color:
 Suppose our input video stream is handled
by vidDevice object.

47.  Step 1: First acquire an RGB Frame from the
Video.
MATLAB Code: rgbFrame = step(vidDevice);

48.  Step 2: Extract the Red Layer Matrix from the RGB
frame.
 MATLAB Code: redFrame = rgbFrame(:,:,1);

49.  Step 3: Get the grey image of the RGB frame.
 MATLAB Code: grayFrame = rgb2gray(rgbFrame);

50.  Step 4: Subtract the grayFrame from the redFrame.
 MATLAB Code: diffFrame =
imsubtract(redFrame, grayFrame);

51.  Step 5: Filter out unwanted noises using Median Filter
 MATLAB Code: diffFrame = medfilt2(diffFrame, [3 3])
 Step 6: Now convert the diffFrame into
corresponding Binary Image using proper threshold
value. Change its value for different light conditions.
Suppose in my code I have used its value as 0.15.
 MATLAB Code: binFrame =
im2bw(diffFrame, 0.15);

52.  Step 7: Now you are all done. Your Red color has been
detected

53. Object tracking means tracing the progress of objects as they
move about in visual scene.
Object tracking, thus, involves processing spatial as well as
temporal changes.
Significant progress has been made in object tracking.
Taxonomy of moving object detection is been proposed.
Performance of various object detection is also compared.

54.  http://www.mathworks.in/help/vision/examples/motion
-based-multiple-object-tracking.html
 http://opencv-srf.blogspot.in/
 http://unoccio.blogspot.in/2009/03/fast-color-based-
object-tracking-using.html
 www.slideshare.com
 http://www.mathworks.in/help/vision/ug/track-an-
object-using-correlation.html
 http://www.codeproject.com/Articles/139628/Detect-
and-Track-Objects-in-Live-Webcam-Video-base
 http://scien.stanford.edu/pages/labsite/2002/ee392j/sebe
_report.pdf