Region Based Object Tracking Algorithm using Intensity Surface Information.

Date of Submission

December 2003

Date of Award

Winter 12-12-2004

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Electronics and Communication Sciences Unit (ECSU-Kolkata)


Mukherjee, Dipti Prasad (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

We propose an algorithm for object detection and tracking in video image sequence. Our algorithm starts from a single point, considered as the center of the object, for tracking. The user in the first frame initializes this point. The basic principle of the algorithm depends on surface approximation and its normal. The surface is approximated on the image data representing a sub-section of an image and this sub-section encloses an object that is to be identified for tracking. Least Square Surface fitting technique is used for the surface approximation. We introduce three external forces from the surface normal that can stretch an active contour from the initialized center of an object towards its boundary. In our algorithm, calculation of spatial movements of the object is governed by the principle of error minimization. The error term is computed from the change of the surface and its normal in advance of time. The algorithm is tested on both synthetic and real image sequences.


ProQuest Collection ID:

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


This document is currently not available here.