DYNAMIC CAMERA CALIBRATION OF ROADSIDE TRAFFIC MANAGEMENT CAMERAS
The authors of this paper present a new algorithm for calibrating roadside traffic management cameras. They describe a simplified camera model that is capable of producing good single vehicle speed estimates. In the paper they describe a detailed model of the roadway scene suitable for analysis by means of computer vision techniques. Using perpendicular information extracted from the vehicles themselves they estimate the position of the camera relative to the highway. They also explain how to find the orientation and focal length of the camera based on measurements of the road boundaries. Their work shows that uncalibrated surveillance video cameras can be used to augment inductance loops as traffic condition sensors or replace loop sensors where it is not cost effective to install inductance loops.
-
Supplemental Notes:
- Publication Date: 2002. IEEE Service Center, Piscataway NJ
-
Corporate Authors:
Guo li jiao tong da xue (China : Republic : 1949- )
,University of Minnesota, Minneapolis
Artificial Intelligence, Robotics, and Vision Lab
Minneapolis, MN United States 55455-0220University of Washington, Seattle
Department of Electrical Engineering
Seattle, WA United States 98195University of Arizona, Tucson
Center for Excellence in Advanced Traffic and Logistics Algorithms and Systems
Tucson, AZ United States 85721National Consortium for Remote Sensing in Transportation (U.S.)
,National University of Singapore. Laboratories for Information Technology
,Omron Corporation
Traffic Solutions Division
2-2-1, Nishikusatsu,
Kusatsu-city, Shiga-prefecture Japan 525-0035Ohio State University, Columbus
Department of Electrical Engineering
Columbus, OH United States 43210 -
Authors:
- Schoepflin, Todd N
- Dailey, Daniel J
- Conference:
- Publication Date: 2002
Language
- English
Media Info
- Pagination: p. 25-30
Subject/Index Terms
- TRT Terms: Cameras; Closed circuit television; Traffic surveillance
Filing Info
- Accession Number: 00974446
- Record Type: Publication
- Source Agency: UC Berkeley Transportation Library
- Files: PATH
- Created Date: Jun 2 2004 12:00AM