Detection and classification of moving objects for an automated surveillance system

Automated surveillance system has been the subject of much research recently. A completely automated system means a computer will perforin the entire task from low level detection to higher level motion analysis. Since conventional system practically using human power to monitor and did not appli...

Full description

Saved in:

Bibliographic Details
Main Author:	Md Tomari, Mohd Razali
Format:	Thesis
Language:	English
Published:	2006
Subjects:	TK7800-8360 Electronics
Online Access:	http://eprints.uthm.edu.my/3179/1/MOHD%20RAZALI%20BIN%20MD%20TOMARI%20-%2024p.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.3179
record_format	uketd_dc
spelling	my-uthm-ep.31792021-11-02T02:00:25Z Detection and classification of moving objects for an automated surveillance system 2006-09 Md Tomari, Mohd Razali TK7800-8360 Electronics Automated surveillance system has been the subject of much research recently. A completely automated system means a computer will perforin the entire task from low level detection to higher level motion analysis. Since conventional system practically using human power to monitor and did not applicable for a long hour monitoring, thus automated system had been created to replace the conventional system. This thesis focuses on a method to detect and classify a moving object that pass through the surveillance area boundary. Moving object is detected by using combination of two frame differencing and adaptive image averaging with selectivity. Technically, this method estimate the motion area before updates the background by taking a weighted average of non-motion area of the current background altogether with non-motion area of the current frame of the video sequence. This step had created a focus of attention for higher level processing and it helps to decrease computation time considerably. The output of a motion-based detector is essentially a collection of foreground that might correspond to the moving objects. But usually the output image produced from this process contaminated with noise and shadow. As a solution, morphological operation has been employed as an approach to remove noise from the foreground object. Mutual shadow that exists with the object had been abolished by combining chromatic colour values with lightness variable. Then, standardized moment invariant is employed to extract the features for each moving blobs. To recognize these blobs, the calculated moment values are fed to a support vector machine module that is equipped with trained extracted moment values for human and vehicle silhouettes. The system operates on colour video imagery from a stationary camera. It can handle object detection in outdoor environments and under changing illumination conditions. The applied post processing module capable to remove noise and shadow from the detected objects with less than 1% of error. Finally, classification algorithm that makes use of the extracted moment values from the detected objects successfully categorize objects into pre-defined classes of human and vehicle with 89.08% of accuracy. All the methods have been tested on video data and the experimental results have demonstrated a fast and robust system 2006-09 Thesis http://eprints.uthm.edu.my/3179/ http://eprints.uthm.edu.my/3179/1/MOHD%20RAZALI%20BIN%20MD%20TOMARI%20-%2024p.pdf text en public mphil masters Universiti Putra Malaysia Faculty of Electrical and Electronic Engineering
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English
topic	TK7800-8360 Electronics
spellingShingle	TK7800-8360 Electronics Md Tomari, Mohd Razali Detection and classification of moving objects for an automated surveillance system
description	Automated surveillance system has been the subject of much research recently. A completely automated system means a computer will perforin the entire task from low level detection to higher level motion analysis. Since conventional system practically using human power to monitor and did not applicable for a long hour monitoring, thus automated system had been created to replace the conventional system. This thesis focuses on a method to detect and classify a moving object that pass through the surveillance area boundary. Moving object is detected by using combination of two frame differencing and adaptive image averaging with selectivity. Technically, this method estimate the motion area before updates the background by taking a weighted average of non-motion area of the current background altogether with non-motion area of the current frame of the video sequence. This step had created a focus of attention for higher level processing and it helps to decrease computation time considerably. The output of a motion-based detector is essentially a collection of foreground that might correspond to the moving objects. But usually the output image produced from this process contaminated with noise and shadow. As a solution, morphological operation has been employed as an approach to remove noise from the foreground object. Mutual shadow that exists with the object had been abolished by combining chromatic colour values with lightness variable. Then, standardized moment invariant is employed to extract the features for each moving blobs. To recognize these blobs, the calculated moment values are fed to a support vector machine module that is equipped with trained extracted moment values for human and vehicle silhouettes. The system operates on colour video imagery from a stationary camera. It can handle object detection in outdoor environments and under changing illumination conditions. The applied post processing module capable to remove noise and shadow from the detected objects with less than 1% of error. Finally, classification algorithm that makes use of the extracted moment values from the detected objects successfully categorize objects into pre-defined classes of human and vehicle with 89.08% of accuracy. All the methods have been tested on video data and the experimental results have demonstrated a fast and robust system
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Md Tomari, Mohd Razali
author_facet	Md Tomari, Mohd Razali
author_sort	Md Tomari, Mohd Razali
title	Detection and classification of moving objects for an automated surveillance system
title_short	Detection and classification of moving objects for an automated surveillance system
title_full	Detection and classification of moving objects for an automated surveillance system
title_fullStr	Detection and classification of moving objects for an automated surveillance system
title_full_unstemmed	Detection and classification of moving objects for an automated surveillance system
title_sort	detection and classification of moving objects for an automated surveillance system
granting_institution	Universiti Putra Malaysia
granting_department	Faculty of Electrical and Electronic Engineering
publishDate	2006
url	http://eprints.uthm.edu.my/3179/1/MOHD%20RAZALI%20BIN%20MD%20TOMARI%20-%2024p.pdf
_version_	1747831020919455744

Detection and classification of moving objects for an automated surveillance system

Similar Items