Date of Award
2010
Publication Type
Master Thesis
Degree Name
M.Sc.
Department
Computer Science
Keywords
Applied sciences
Supervisor
Boubakeur Boufama
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
Object tracking with occlusion handling is a challenging problem in automated video surveillance. Occlusion handling and tracking have always been considered as separate modules. We have proposed an automated video surveillance system, which automatically detects occlusions and perform occlusion handling, while the tracker continues to track resulting separated objects. A new approach based on sub-blobbing is presented for tracking objects accurately and steadily, when the target encounters occlusion in video sequences. We have used a feature-based framework for tracking, which involves feature extraction and feature matching.
Recommended Citation
Alam, Mohammad Omair, "Occlusion handling in multiple people tracking" (2010). Electronic Theses and Dissertations. 8052.
https://scholar.uwindsor.ca/etd/8052