Object-tracking is one of the most popular areas of video processing because of its applicability to daily problems and ease of production, e.g. surveillance cameras, adaptive traffic lights, plane detection, vehicle navigation, human-computer interaction, object-based video compression, smart rooms, driver assistance, perceptual user interface, augmented reality etc. The purpose of object tracking is to determine the position of the object in images continuously and reliably against dynamic scenes. The bases of the work is the mean shift object-tracking algorithm for a moving target in a video by defining a rectangular target window in an initial frame, and then process the data within that window to separate the tracked object from the background. The paper also includes experimental results of the tracking using the mean shift based algorithm with certain improvements to make it suitable for tracking fast moving object.
[1]
Gary Bradski,et al.
Computer Vision Face Tracking For Use in a Perceptual User Interface
,
1998
.
[2]
Tieniu Tan,et al.
A survey on visual surveillance of object motion and behaviors
,
2004,
IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).
[3]
Robert T. Collins,et al.
Mean-shift blob tracking through scale space
,
2003,
2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..
[4]
Alvy Ray Smith,et al.
Color gamut transform pairs
,
1978,
SIGGRAPH.