18-04-2010, 07:59 PM
[attachment=3228]
OBJECT TRACKING AND DETECTION
Presented By
Sneha K. Desai
Under the guidance of:
Mr. Anchi. F. B
Dept. of Computer Science,
R.E.C, Hulkoti.
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.
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.
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
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 automatic moving object detection algorithm for video surveillance applications
Steps:
Moving object detection phase
Moving object extraction phase
Moving object recognition phase
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.
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.
Background updating
The background updating of the selected pixels are replaced by the average of the current and background pixels.
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