Title :
Multiple vehicle detection and tracking in hard real-time
Author :
Betke, Margrit ; Haritaoglu, Esin ; Davis, Larry S.
Author_Institution :
Inst. for Adv. Comput. Studies, Maryland Univ., College Park, MD, USA
Abstract :
A vision system is developed that recognizes and tracks multiple cars from sequences of gray-scale images taken from a moving car in hard real-time. The recognition method is based on feature detection, online deformable template matching, and temporal differencing. The vision system utilizes the hard real-time operating system Maruti which guarantees that the timing constraints on the various processes of the vision system are satisfied. The dynamic creation and termination of tracking processes optimizes the amount of computation resources spent and allows fast real-time recognition and tracking of multiple cars as demonstrated over a large number of image frames
Keywords :
computer vision; feature extraction; image sequences; object recognition; tracking; Maruti; gray-scale images; moving car; multiple vehicle detection; multiple vehicle tracking; online deformable template matching; real-time operating system; temporal differencing; timing constraints; vision system; Cameras; Computer vision; Gray-scale; Image recognition; Machine vision; Real time systems; Scheduling; Timing; Vehicle detection; Vehicle safety;
Conference_Titel :
Intelligent Vehicles Symposium, 1996., Proceedings of the 1996 IEEE
Conference_Location :
Tokyo
Print_ISBN :
0-7803-3652-6
DOI :
10.1109/IVS.1996.566405
