Object Tracking Using Stress Induced Surface Seeking Model.

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

Department

Electronics and Communication Sciences Unit (ECSU-Kolkata)

Supervisor

Mukherjee, Dipti Prasad (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

Detection and tracking of object is one of the basic goals in video image processing. We use a region based active contour model. The proposed model is a modified version of active snake model by Kass et al. (987) [1]. While the original active contour model relies only on edge gradient force. we have designed stress density model for the image region within the object. The image space is assumed as deformable metal plate. The stress distribution on the plate due to presence of an object on the plate is modeled. The intensity of pixels representing object forms the surface where stress energy is calculated. The performance of the proposed algorithm is attractive as it introduced a range of the external force term in this model. We have applied our technique to segment synthetic and real images. It is also shown that the Alorithm can successfully track objects in a real viseo sequence.

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843178

Control Number

ISI-DISS-2003-116

Creative Commons License

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

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/6287

This document is currently not available here.

Share

COinS