Title :
An efficient vision system for multiple car tracking
Author :
Zeng, Zhihong ; Ma, Songde
Abstract :
An efficient vision system is proposed for multiple car tracking on the highway. The main modules of the system are: lane detection, separate 2D model-based trackers (rectangular model for passing car and U-shape model for distant car), heuristic car detection, and a process coordinator. In the system, the dynamical creation and termination of tracking processes optimizes the amount of spent computational resources. The system is successfully tested with the image sequence from PETS2001 and the average processing time per frame is 12 ms on Pentium III 450 MHz PC.
Keywords :
automatic guided vehicles; computer vision; image sequences; target tracking; 12 ms; 450 MHz; PETS2001; Pentium III 450 MHz PC; U-shape model; automatic vehicle guidance; average processing time perframe; distant car; dynamical creation; efficient vision system; heuristic car detection; highway; image sequence; lane detection; multiple car tracking; passing car; process coordinator; rectangular model; separate 2D model-based trackers; spent computational resources; tracking process termination; Content addressable storage; Image sequences; Laboratories; Machine vision; Pattern recognition; Road transportation; Road vehicles; Robustness; Stability; System testing;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048376
