Machine Vision Based Traffic-Adjusted Intersection Signal Control
Machine vision is a branch of the image processing discipline where images are captured for immediate decision making. It is best suited for real time applications such as quality control of manufactured parts and intersection traffic signal control. Research on machine vision based traffic monitoring and control has been conducted since the late 1970s. Recent advances of imaging equipment and microprocessor technology has made machine vision based vehicle detection a practical option compared with conventional traffic detectors. This paper describes some of the available machine vision systems and how they can be effectively used for traffic control at an intersection. A set of rules has been defined which makes use of the various parameters obtained from the imaging system and allocates the optimum signal timings to the different phases. The overall efficiency of the traffic control system would still hinge on all these predefined rules.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/0872629791
-
Corporate Authors:
American Society of Civil Engineers
1801 Alexander Bell Drive
Reston, VA United States 20191-4400 -
Authors:
- Chou, Eddie Y J
- Sethi, Vaneet
-
Conference:
- Digital Image Processing: Techniques and Applications in Civil Engineering
- Location: Kona Hawaii, United States
- Date: 1993-2-28 to 1993-3-5
- Publication Date: 1993
Language
- English
Media Info
- Media Type: Print
- Features: Figures; References;
- Pagination: pp 150-157
- Monograph Title: Digital Image Processing: Techniques and Applications in Civil Engineering
Subject/Index Terms
- TRT Terms: Image analysis; Image processing; Intersection elements; Machine vision; Real time information; Signalized intersections; Traffic signal control systems; Traffic signal timing; Traffic surveillance; Vehicle detectors
- Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning;
Filing Info
- Accession Number: 01055683
- Record Type: Publication
- ISBN: 0872629791
- Files: TRIS
- Created Date: Aug 23 2007 3:10PM