Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video

A vehicle counting and tracking system automatically detects and classifies vehicles from traffic surveillance video sequences. The system are used to replace manual labor to collect vehicles data for various application such as transportation planning and road safety evaluation. The existing Vehicl...

Full description

Saved in:

Bibliographic Details
Main Author:	Kueh , Chiung Lin
Format:	Thesis
Language:	English
Published:	2015
Subjects:	TK1-9971 Electrical engineering Electronics Nuclear engineering
Online Access:	http://eprints.usm.my/40817/1/KUEH_CHIUNG_LIN_24_pages.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.40817
record_format	uketd_dc
spelling	my-usm-ep.408172018-06-26T07:24:27Z Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video 2015 Kueh , Chiung Lin TK1-9971 Electrical engineering. Electronics. Nuclear engineering A vehicle counting and tracking system automatically detects and classifies vehicles from traffic surveillance video sequences. The system are used to replace manual labor to collect vehicles data for various application such as transportation planning and road safety evaluation. The existing Vehicle Detection and Classification System does not have tracking and counting module implemented. Tracking is required to enable automatic vehicle count. The objective of this project is to develop and implement tracking and counting feature into the existing vehicle detection and classification system, assess the vehicle detection and classification with tracking and counting feature system performances, and select the optimal parameters for tracking and counting module. Visual Background Extractor (ViBE) is used to extract the vehicles (foreground) from the traffic surveillance video sequences. Simple tracking and counting algorithm is used to track and count the detected vehicle. Histogram of Oriented Gradient (HOG) is used to extract features from the detected vehicle. Multi-class Support Vector Machine (SVM) is used to classify the detected vehicle into four classes, which are motorcycle, car, lorry, and non-vehicle. The system is evaluated using two video sequences which are 670 seconds long with total of 20100 frames. The overall system performance achieves 78.19 % and 88.14% for vehicle detection and classification, respectively. 2015 Thesis http://eprints.usm.my/40817/ http://eprints.usm.my/40817/1/KUEH_CHIUNG_LIN_24_pages.pdf application/pdf en public masters Universiti Sains Malaysia Pusat Pengajian Kejuruteraan Elektrik dan Elektronik
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	TK1-9971 Electrical engineering Electronics Nuclear engineering
spellingShingle	TK1-9971 Electrical engineering Electronics Nuclear engineering Kueh , Chiung Lin Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
description	A vehicle counting and tracking system automatically detects and classifies vehicles from traffic surveillance video sequences. The system are used to replace manual labor to collect vehicles data for various application such as transportation planning and road safety evaluation. The existing Vehicle Detection and Classification System does not have tracking and counting module implemented. Tracking is required to enable automatic vehicle count. The objective of this project is to develop and implement tracking and counting feature into the existing vehicle detection and classification system, assess the vehicle detection and classification with tracking and counting feature system performances, and select the optimal parameters for tracking and counting module. Visual Background Extractor (ViBE) is used to extract the vehicles (foreground) from the traffic surveillance video sequences. Simple tracking and counting algorithm is used to track and count the detected vehicle. Histogram of Oriented Gradient (HOG) is used to extract features from the detected vehicle. Multi-class Support Vector Machine (SVM) is used to classify the detected vehicle into four classes, which are motorcycle, car, lorry, and non-vehicle. The system is evaluated using two video sequences which are 670 seconds long with total of 20100 frames. The overall system performance achieves 78.19 % and 88.14% for vehicle detection and classification, respectively.
format	Thesis
qualification_level	Master's degree
author	Kueh , Chiung Lin
author_facet	Kueh , Chiung Lin
author_sort	Kueh , Chiung Lin
title	Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
title_short	Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
title_full	Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
title_fullStr	Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
title_full_unstemmed	Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video
title_sort	development of vehicle tracking and counting system from traffic surveillance video
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Kejuruteraan Elektrik dan Elektronik
publishDate	2015
url	http://eprints.usm.my/40817/1/KUEH_CHIUNG_LIN_24_pages.pdf
_version_	1747820829274537984

Development Of Vehicle Tracking And Counting System From Traffic Surveillance Video

Similar Items