Real-time traffic monitoring
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Traffic statistics desired by road engineers and planners,and "traffic warning" systems demand real-timeperformance which precludes the use of batch processing.We apply recent real-time tracking techniquesalong with scene specific tuning of the dynamics toenable the tracker to accurately predict target locationand thus reduce the amount of search and/or imageprocessing required. The benefits of learning dynamicsfor accurate prediction are speed -- our tracker operatesat frame rate --...Keywords
This publication has 14 references indexed in Scilit:
- Vision-based car-following: detection, tracking, and identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Towards active exploration of static and dynamic scene geometryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- 3D position, attitude and shape input using video tracking of hands and lipsPublished by Association for Computing Machinery (ACM) ,1994
- Association of motion verbs with vehicle movements extracted from dense optical flow fieldsPublished by Springer Nature ,1994
- A framework for spatiotemporal control in the tracking of visual contoursInternational Journal of Computer Vision, 1993
- Model-based object tracking in monocular image sequences of road traffic scenesInternational Journal of Computer Vision, 1993
- Understanding object motion: Recognition, learning and spatiotemporal reasoningRobotics and Autonomous Systems, 1991
- On the use of motion concepts for top-down control in traffic scenesPublished by Springer Nature ,1990
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- Model-based vision: a program to see a walking personImage and Vision Computing, 1983