An Integrated Multi-Camera Vehicle Tracking System

碩士 === 亞洲大學 === 資訊工程學系碩士班 === 96 === With advance of technology, almost every household in our society today owns more than one car, and that is the reason that brings about our traffic jam. Therefore, when there is accident or one is to investigate suspicious cars in various crimes, it has become v...

Full description

Bibliographic Details
Main Authors: Zheng Quan-Wei, 鄭權偉
Other Authors: Chen Shih-Nung
Format: Others
Language:zh-TW
Published: 2008
Online Access:http://ndltd.ncl.edu.tw/handle/85147292056173216049
Description
Summary:碩士 === 亞洲大學 === 資訊工程學系碩士班 === 96 === With advance of technology, almost every household in our society today owns more than one car, and that is the reason that brings about our traffic jam. Therefore, when there is accident or one is to investigate suspicious cars in various crimes, it has become very difficult. As a result, when there is any accident or event, the police always have to spend a great amount of manpower and resources to find out the suspicious cars before clues to resolve the case can be obtained. This paper used computer vision technology to develop an integrated multi-camera vehicle tracking system. And vehicle information detected on the system will be transmitted to the network database. Then, relevant personnel can use the web browser to inquire the record results so that users can quickly discover the car they are after. The proposed system can follow cars of different size, and colors. In addition, the system can also lock on the possible route of transportation on the car, and provide information of tracking-down to relevant personnel or authorities for employment. The design of the proposed system, in comparison to other systems, is given with advantages of fast speed, simplicity, tracking-down on several cars concurrently, detection at several road junctions, detection of vehicle color, and significant efficiency in real-time detection. With tests of several road films, the system has proven with favorable results, and it is believed the system can be most helpful to track down on vehicles.