CONTENTS

1. Introduction to object tracking

2. Object representation
3. Feature selection for tracking
4. Algorithm for object tracking
5. Introduction to object detection
6. Moving object detection algorithms
7. Advantages and disadvantages of moving object detection
8. conclusion
OBJECT TRACKING
A method of following an object through successive image frames
to determine its relative movement with respect to other objects.
SCHEMATIC REPRESENTATION OF GENERIC OBJECT TRACKING SYSTEM

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.
OBJECT REPRESENTATION
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.
• 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.
FEATURE SELECTION FOR TRACKING

The common visual features are as follows:

• Color: The apparent color of an object is influenced by two

factors i.e. spectral power distribution of illuminant and
surface reflectance properties.

• Edges: Object boundaries generate strong changes in the image

intensities. Edge detection is used to identify these changes
• Optical Flow: Optical flow is a dense field of displacement
vectors which defines the translation of each pixel in a region. It
is computed using the brightness constraints.

• Texture: Texture is a measure of the intensity variation of the

surface which quantifies properties such as smoothness and
regularity.
 ALGORITHM FOR OBJECT TRACKING
Background Subtraction in Videos using Bayesian Learning

BMA
OBJECT DETECTION
Object detection from video sequence is the process of detecting
the moving objects in frame sequence using digital image
processing techniques.

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
 TAXONOMY OF MOVING OBJECT DETECTION ALGORITHMS

FD BS FD & BS BUT CC

1.An improved 1.Real time 1.A moving 1.A moving 1.Detect

moving object moving object object detection & track
detection object detection algorithm on moving
algorithm detection algorithm color object
2.A moving for video based on information using
object detection monitoring improved partitio-
algorithm for system background ning &
smart cameras subtraction normal-
3.An automatic ized
object detection cross
algorithm for correlat-
video ion
surveillance
application
FRAME DIFFERENCE
In this method a background image without any moving objects
of interest is taken as reference image.
Pixel value for each co-ordinate (x, y) for each color channel of the
background image is subtracted from corresponding pixel value of
input image.
If resulting value is greater than a particular threshold value, then
that is foreground pixel otherwise background.
AN IMPROVED MOVING OBJECT DETECTION ALGORITHM
BASED ON FRAME DIFFERENCE AND EDGE DETECTION

a)Frame(k-1) taken at time t b)Frame(k) taken at time t+1

c)Edge map(EDGE k-1) of d)Edge map(EDGE k) of

Frame(k-1) Frame(k)
 e)Edge difference image D( x, y) f)Obtained motion areas are then
highlighting the difference of mapped to the original image &
edge maps of Frame(k-1) & appropriate edge pixels(white
Frame(k) pixels) are highlighted

From the above result we can see that the frame differencing based
on the edge detection is a simple method for detecting for moving
objects and gives better results
 A MOVING OBJECT DETECTION ALGORITHM FOR
SMART CAMERAS
Flow diagram
image Signed difference Calculate motion
strength

Detect & Link motion blocks result

AN AUTOMATIC MOVING OBJECT DETECTION ALGORITHM
FOR VIDEO SURVEILLANCE APPLICATIONS

Steps:
 Moving object detection phase
 Moving object extraction phase
 Moving object recognition phase
OBJECT DETECTION PHASE:

1st Image reference Difference

deterministic rule,
image Thresholding &
background
compensation

Difference image 3rd image output

image

2nd Image input

image
OBJECT EXTRACTION PHASE:
Implementation steps of extraction:
• Horizontal Scanning
• Vertical Scanning

Threshold
Comparison eliminate
Deterministic phantom
rule object &
frame
BACKGROUND SUBTRACTION

The moving object regions are detected by subtracting the current

image pixel-by-pixel from a reference background image.
The pixel where the difference is above a threshold are classified
as foreground otherwise background.
Morphological post processing operations are performed to reduce
the effects of noise and enhance the detected object.
 REAL-TIME MOVING OBJECT DETECTION FOR VIDEO
MONITORING SYSTEMS
Flowchart of background updating
Experiments:
Comparison of background images

Fig 1 Fig 2

Fig 1 shows the shadow on right-top corner of the image.

Fig 2 shows the background image by using self-adaptive updating
of background image
Background image of 35th frame Background image of 105th frame

Background image of 175th frame

Moving vehicle of 35th frame Moving vehicle of 105th frame

Moving vehicle of 175th frame

 FRAME DIFFERENCE AND
BACKGROUND SUBTRACTION

The combination of background subtraction and frame differencing

can improve the detection speed and overcome the lack of
sensitivity of light changes.
MOVING OBJECT DETECTION ALGORITHM BASED ON
IMPROVED BACKGROUND SUBTRACTION

Original images Result obtained after using Gaussian mixed

model
Foreground image masked original image
 BACKGROUND UPDATING

The background updating of the selected pixels are replaced by the

average of the current and background pixels.
 A MOVING OBJECT DETECTION ALGORITHM BASED ON
COLOR INFORMATION

shows the origin image, and shows the result of origin shows the detected result
the color of pedestrian’s MOG detection, and legs of improved MOG, and
pants is adjacent to the floor which are overlap with floor legs which were overlap
color. can’t be detected with floor can be detected
completely. completely.
 shows the color image background model show the final detected
segmentation result with result of joint color image
the edged image. segmentation and
background model.
 CROSS CORRELATION
MOVING OBJECT TRACKING AND DETECTING USING
PARTITIONING AND NORMALIZED CROSS CORRELATION

Basic Steps:

Partitioning of two
consecutive frames

Moving object detection

using Cross Correlation

Identify moving object’s

location and perform tracking
The tracking sequence of a walking person. This walking person is pointed by a red star.

Tracking sequence of multiple objects by simple difference method

Tracking sequence of multiple objects by PNCC method
 CONCLUSION
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.
Certain features of those objects have to be selected for tracking.
These features need to be matched over different frames.
Significant progress has been made in object tracking.
Taxonomy of moving object detection is been proposed.
Performance of various object detection is also compared.

So, atlast it is noted that algorithm based on frame difference

and edge detection has detection accuracy and high detection
speed
Thank you
