Multiple Vehicle Detection and Segmentation in Malaysia Traffic Flow

Malaysian Technical Universities Conference on Engineering and Technology 2017

Hasan, Ahmad Fariz^1 ; Che Husin, Mohd Fikri^1 ; Rosli, Khairul Affendi^1 ; Hashim, Mohd Norhafiz^1 ; Zainal Abidin, Amar Faiz^2

Department of Electronic Engineering Technology, Faculty of Engineering Technology, Universiti Malaysia, Perlis, Malaysia^1

Faculty of Engineering Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal Melaka

76100, Malaysia^2

关键词: Closed circuit television;    Experimental validations;    Intelligent transportation systems;    Number of vehicles;    Optical flow estimation;    Traffic monitoring;    Traffic surveillance;    Vision based system;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/318/1/012041/pdf
DOI  :  10.1088/1757-899X/318/1/012041

来源: IOP

【 摘 要 】

Vision based system are widely used in the field of Intelligent Transportation System (ITS) to extract a large amount of information to analyze traffic scenes. By rapid number of vehicles on the road as well as significant increase on cameras dictated the need for traffic surveillance systems. This system can take over the burden some task was performed by human operator in traffic monitoring centre. The main technique proposed by this paper is concentrated on developing a multiple vehicle detection and segmentation focusing on monitoring through Closed Circuit Television (CCTV) video. The system is able to automatically segment vehicle extracted from heavy traffic scene by optical flow estimation alongside with blob analysis technique in order to detect the moving vehicle. Prior to segmentation, blob analysis technique will compute the area of interest region corresponding to moving vehicle which will be used to create bounding box on that particular vehicle. Experimental validation on the proposed system was performed and the algorithm is demonstrated on various set of traffic scene.