Smart objects identification system for robotic surveillance

Video surveillance is an active research topic in computer vision. In this paper, humans and cars identification technique suitable for real time video surveillance systems is presented. The technique we proposed includes background subtraction, foreground segmentation, shadow removal, feature ext...

Full description

Bibliographic Details
Main Authors:	Rashid , Muhammad Mahbubur, Shafie, Amir Akramin, Mohd Ibrahim, Azhar
Format:	Article
Language:	English
Published:	Institute of Automation, Chinese Academy of Sciences and Springer-Verlag Berlin Heidelberg 2014
Subjects:	TK1001 Production of electric energy. Powerplants
Online Access:	http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/1/Smart%2BObjects%2BIdentification%2BSystem%2Bfor%2BRobotic%2BSurveillance.pdf

id	iium-35901
recordtype	eprints
spelling	iium-359012019-04-05T01:35:27Z http://irep.iium.edu.my/35901/ Smart objects identification system for robotic surveillance Rashid , Muhammad Mahbubur Shafie, Amir Akramin Mohd Ibrahim, Azhar TK1001 Production of electric energy. Powerplants Video surveillance is an active research topic in computer vision. In this paper, humans and cars identification technique suitable for real time video surveillance systems is presented. The technique we proposed includes background subtraction, foreground segmentation, shadow removal, feature extraction and classification. The feature extraction of the extracted foreground objects is done via a new set of affine moment invariants based on statistics method and these were used to identify human or car. When the partial occlusion occurs, although features of full body cannot be extracted, our proposed technique extracts the features of head shoulder. Our proposed technique can identify human by extracting the human head-shoulder up to 60%–70% occlusion. Thus, it has a better classification to solve the issue of the loss of property arising from human occluded easily in practical applications. The whole system works at approximately 16−29 fps and thus it is suitable for real-time applications. The accuracy for our proposed technique in identifying human is very good, which is 98.33%, while for cars� identification, the accuracy is also good, which is 94.41%. The overall accuracy for our proposed technique in identifying human and car is at 98.04%. The experiment results show that this method is effective and has strong robustness. Institute of Automation, Chinese Academy of Sciences and Springer-Verlag Berlin Heidelberg 2014-02 Article PeerReviewed application/pdf en http://irep.iium.edu.my/35901/1/Smart%2BObjects%2BIdentification%2BSystem%2Bfor%2BRobotic%2BSurveillance.pdf Rashid , Muhammad Mahbubur and Shafie, Amir Akramin and Mohd Ibrahim, Azhar (2014) Smart objects identification system for robotic surveillance. International Journal of Automation and Computing , 11 (1). pp. 59-71. ISSN 1476-8186 http://www.ijac.net/EN/volumn/home.shtml 10.1007/s11633-014-0766-9
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	TK1001 Production of electric energy. Powerplants
spellingShingle	TK1001 Production of electric energy. Powerplants Rashid , Muhammad Mahbubur Shafie, Amir Akramin Mohd Ibrahim, Azhar Smart objects identification system for robotic surveillance
description	Video surveillance is an active research topic in computer vision. In this paper, humans and cars identification technique suitable for real time video surveillance systems is presented. The technique we proposed includes background subtraction, foreground segmentation, shadow removal, feature extraction and classification. The feature extraction of the extracted foreground objects is done via a new set of affine moment invariants based on statistics method and these were used to identify human or car. When the partial occlusion occurs, although features of full body cannot be extracted, our proposed technique extracts the features of head shoulder. Our proposed technique can identify human by extracting the human head-shoulder up to 60%–70% occlusion. Thus, it has a better classification to solve the issue of the loss of property arising from human occluded easily in practical applications. The whole system works at approximately 16−29 fps and thus it is suitable for real-time applications. The accuracy for our proposed technique in identifying human is very good, which is 98.33%, while for cars� identification, the accuracy is also good, which is 94.41%. The overall accuracy for our proposed technique in identifying human and car is at 98.04%. The experiment results show that this method is effective and has strong robustness.
format	Article
author	Rashid , Muhammad Mahbubur Shafie, Amir Akramin Mohd Ibrahim, Azhar
author_facet	Rashid , Muhammad Mahbubur Shafie, Amir Akramin Mohd Ibrahim, Azhar
author_sort	Rashid , Muhammad Mahbubur
title	Smart objects identification system for robotic surveillance
title_short	Smart objects identification system for robotic surveillance
title_full	Smart objects identification system for robotic surveillance
title_fullStr	Smart objects identification system for robotic surveillance
title_full_unstemmed	Smart objects identification system for robotic surveillance
title_sort	smart objects identification system for robotic surveillance
publisher	Institute of Automation, Chinese Academy of Sciences and Springer-Verlag Berlin Heidelberg
publishDate	2014
url	http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/ http://irep.iium.edu.my/35901/1/Smart%2BObjects%2BIdentification%2BSystem%2Bfor%2BRobotic%2BSurveillance.pdf
first_indexed	2023-09-18T20:51:25Z
last_indexed	2023-09-18T20:51:25Z
_version_	1777410019395895296

Smart objects identification system for robotic surveillance

Similar Items