19-09-2012, 03:31 PM
Moving Object Tracking in Video Using MATLAB
Moving Object.pdf (Size: 1.03 MB / Downloads: 174)
Abstract
In this paper a method is described for tracking
moving objects from a sequence of video frame. This method is
implemented by using optical flow (Horn-Schunck) in matlab
simulink. It has a variety of uses, some of which are: humancomputer
interaction, security and surveillance, video
communication and compression, augmented reality, traffic
control, medical imaging and video editing.
INTRODUCTION
The objective of this project is to identify and track a
moving object within a video sequence. The tracking of the
object is based on optical flows among video frames in
contrast to image background-based detection. The proposed
optical flow method is straightforward and easier to
implement and we assert has better performance. The project
consist of software simulation on Simulink and can be
implemented as hardware on TI TMS320DM6437 DSP
board. The idea of this project is derived from the tracking
section of the demos listed in MATLAB computer vision
toolbox website.
DESIGN AND IMPLEMENTATION
In this Simulink model, there are couple of major
parameters that we need to adjust depending what the
tracking object is. The first parameter is the gain after the
mean blocks in the velocity threshold subsystem. If too much
background noise besides the moving objects is included in
the output intensity matrix, the gain need to be adjust to filter
out background in the image. The second parameter is the
constant that is used for comparison with the boundary box.
Any boundary boxes with area below this constant is filter
out. One of the disadvantages of optical flow based tracking
is that a moving object may have many small boundary boxes
due to the optical detection on different part of the moving
object. In order to better keep track of the moving object, we
need to filter out the small boundary boxes and keep the large
boundary box. The other minor parameters such as the shape
for the display of motion vector and tracking box are up for
the users to decide
Optical flow
Optical flow or optic flow is the pattern of apparent motion of
objects, surfaces, and edges in a visual scene caused by the
relative motion between an observer (an eye or a camera) and
the scene.[2][3] The concept of optical flow was first studied in
the 1940s and ultimately published by American
psychologist James J. Gibson[4] as part of his theory of
affordance. Optical flow techniques such as motion detection,
object segmentation, time-to-collision and focus of expansion
calculations, motion compensated encoding, and stereo
disparity measurement utilize this motion of the objects'
surfaces and edges.