No Detail Found!

HOG approach for human novelty activity detection.

Author(s)
Abdul-Lateef Yussiff Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Tronoh, Perak, Malaysia
Suet-Peng Yong Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Tronoh, Perak, Malaysia
Baharum B. Baharudin Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Tronoh, Perak, Malaysia
Muhammad Azeem Abbas University Institute of Information Technology, PMAS-Arid Agriculture University, Rawalpindi, Pakistan
Abstract
Surveillance system is one of the most active research areas in the computer vision, there has not been much improvement in automating the surveillances due to human behavior being versatile and it is not easy to capture every single human behaviour abnormalities. We have addressed the most fundamental task of every computer vision project which is detection human in images and surveillance. We adopted a sliding window technique based on Histogram of Oriented Gradient (HOG) as features in detecting human in images. Our Method achieves 56.41% F-score and 88.71% precision when applied to Bank security image dataset.
Publication Details
Page(s) 741-744
DOI DOI not available
Published Journal: Science International, Volume: 25, Issue: 4, Year: 2013

Request the full text from PASTIC

More from Science International
0

Citations

0

Downloads

42

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk