Redefining histograms of oriented gradients descriptors for handling occlusion in people detection

Object detection is a big challenge for researchers to address the issues that affect accurate detections. The Histogram of oriented gradients (HOG) descriptors have been used extensively for object detection on challenging conditions with good results. However, occlusion remains a well-known issue...

Full description

Saved in:

Bibliographic Details
Main Author:	Sani, Ahmad
Format:	Thesis
Language:	English
Published:	2014
Subjects:	QA Mathematics
Online Access:	http://eprints.utm.my/id/eprint/48597/1/AhmadSaniMFC2014.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.48597
record_format	uketd_dc
spelling	my-utm-ep.485972020-02-06T01:16:23Z Redefining histograms of oriented gradients descriptors for handling occlusion in people detection 2014 Sani, Ahmad QA Mathematics Object detection is a big challenge for researchers to address the issues that affect accurate detections. The Histogram of oriented gradients (HOG) descriptors have been used extensively for object detection on challenging conditions with good results. However, occlusion remains a well-known issue where some parts of an object are only visible. Conventional frameworks using HOG descriptors for detecting whole human body are prone to occluded people and thus causing errors on implementations running these frameworks. This issue was addressed in different approaches like hybrid feature extraction algorithms. Rather than following such approaches, the problem is addressed in this research by redefining HOG descriptors to work in a part object (body) detection framework that is powered by a finite-state machine. Experiments were conducted to test a new method of extracting HOG descriptors for parts of human body via slicing a window’s HOG descriptor into four. The part body detection framework utilises each part’s descriptor whereas three detected parts are sufficient to declare that the window has an assumed instance. Support vector machines (SVM) were used to classify the extracted parts and a finite- state machine was employed for handling the detected parts. Training and testing were made on subsets from the INRIA Person Dataset and the results favoured the part body detection framework over the conventional whole body framework. For a test set of 50 positive images of occluded people, the part body detection framework successfully detected 46 true positive while the whole body framework detected 36. Moreover, the former had less false positive detection than the latter having 80 false positive windows comparing to 289. 2014 Thesis http://eprints.utm.my/id/eprint/48597/ http://eprints.utm.my/id/eprint/48597/1/AhmadSaniMFC2014.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:86181?queryType=vitalDismax&query=Redefining+histograms+of+oriented+gradients+descriptors+for+handling+occlusion+in+people+detection&public=true masters Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA Mathematics
spellingShingle	QA Mathematics Sani, Ahmad Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
description	Object detection is a big challenge for researchers to address the issues that affect accurate detections. The Histogram of oriented gradients (HOG) descriptors have been used extensively for object detection on challenging conditions with good results. However, occlusion remains a well-known issue where some parts of an object are only visible. Conventional frameworks using HOG descriptors for detecting whole human body are prone to occluded people and thus causing errors on implementations running these frameworks. This issue was addressed in different approaches like hybrid feature extraction algorithms. Rather than following such approaches, the problem is addressed in this research by redefining HOG descriptors to work in a part object (body) detection framework that is powered by a finite-state machine. Experiments were conducted to test a new method of extracting HOG descriptors for parts of human body via slicing a window’s HOG descriptor into four. The part body detection framework utilises each part’s descriptor whereas three detected parts are sufficient to declare that the window has an assumed instance. Support vector machines (SVM) were used to classify the extracted parts and a finite- state machine was employed for handling the detected parts. Training and testing were made on subsets from the INRIA Person Dataset and the results favoured the part body detection framework over the conventional whole body framework. For a test set of 50 positive images of occluded people, the part body detection framework successfully detected 46 true positive while the whole body framework detected 36. Moreover, the former had less false positive detection than the latter having 80 false positive windows comparing to 289.
format	Thesis
qualification_level	Master's degree
author	Sani, Ahmad
author_facet	Sani, Ahmad
author_sort	Sani, Ahmad
title	Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
title_short	Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
title_full	Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
title_fullStr	Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
title_full_unstemmed	Redefining histograms of oriented gradients descriptors for handling occlusion in people detection
title_sort	redefining histograms of oriented gradients descriptors for handling occlusion in people detection
granting_institution	Universiti Teknologi Malaysia, Faculty of Computing
granting_department	Faculty of Computing
publishDate	2014
url	http://eprints.utm.my/id/eprint/48597/1/AhmadSaniMFC2014.pdf
_version_	1747817429296218112

Redefining histograms of oriented gradients descriptors for handling occlusion in people detection

Similar Items