Detection and Tracking of Humans in Video.

Date of Submission

December 2015

Date of Award

Winter 12-12-2016

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Machine Intelligence Unit (MIU-Kolkata)

Supervisor

Murthy, C. A. (MIU-Kolkata; ISI)

Abstract (Summary of the Work)

This objective of this thesis is to detect the presence of moving people and count the number of individuals in a given video. The problem is to identify motion regions in the video, separate the motion regions from the static background, form foreground objects from the motion regions, classify each object to determine if it is a person, then track each person detected throughout the duration of the video.Our focus is to improve the classification accuracy by using new features that are based on pairwise distance between training points in feature space, and reduce the dimensionality of the feature space by applying a data condensation method prior to feature extraction. The proposed method gives better accuracy and lower misclassification rate on a benchmark image dataset, as well as a higher tracking accuracy on video datasets.

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:28843128

Control Number

ISI-DISS-2015-329

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/10263/6486

This document is currently not available here.

Share

COinS