AUTOMATIC INCIDENT DETECTION THROUGH VIDEO IMAGE PROCESSING
Automatic Incident Detection is one of the major challenges in urban freeway operations. In spite of recent efforts worldwide, fast and reliable Automatic Incident Detection has been elusive. To a large extent this can be attributed to the limitations of existing detection devices. To overcome this problem, a new wide-area video detection system called AUTOSCOPE was recently developed in Minnesota and was installed in the field for rigorous around-the-clock testing for over two years. As a result, AUTOSCOPE was substantially improved, weatherized and expanded to multiple camera units. Subsequently an incident detection system was developed, based on AUTOSCOPE measurements, installed at a site in Minneapolis and evaluated under continuous around-the-clock, real-time operation for over four months. In parallel to this, a 39-camera, seven-mile, machine vision, live laboratory was designed on Interstate-394 for full deployment and validation of the incident detection system. In this paper the development and testing of the machine vision-based incident detection system is presented, along with the long-term AUTOSCOPE test results and plans for future improvements.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/00410683
-
Corporate Authors:
Printerhall Limited
29 Newmart Street
London W1P 3PE, England -
Authors:
- Michalopoulos, P G
- Jacobson, R D
- ANDERSON, C A
- DeBruycker, T B
- Publication Date: 1993-2
Language
- English
Media Info
- Features: Figures; References; Tables;
- Pagination: p. 66-75
-
Serial:
- Traffic Engineering & Control
- Volume: 34
- Issue Number: 2
- Publisher: Hemming Group, Limited
- ISSN: 0041-0683
- Serial URL: http://www.tecmagazine.com/
Subject/Index Terms
- TRT Terms: Automatic incident detection; Detectors; Field tests; Freeways; Incident detection; Urban areas
- Uncontrolled Terms: Video technology
- Old TRIS Terms: Detection systems; Urban freeways
- Subject Areas: Highways; Operations and Traffic Management; Safety and Human Factors;
Filing Info
- Accession Number: 00634078
- Record Type: Publication
- Files: TRIS, ATRI
- Created Date: Jun 14 1993 12:00AM