A low-cost strong shadow-based segmentation approach for vehicle tracking in congested traffic scenes

Ehsan Adeli Mosabbeb, Maryam Sadeghi, Mahmood Fathy, Maliheh Bahekmat
2007 2007 International Conference on Machine Vision  
In this paper, a vehicle tracking algorithm is proposed that uses a new approach to deal with occlusion. This approach uses the novel feature, recently proposed to improve the accuracy of localization and occlusion handling. It was constructed on the basis of the strong shadow under the vehicle in real-world traffic scenes. In this paper, some statistical parameters of each frame are used to detect and segment these shadows. To demonstrate robustness and accuracy of our proposed approach,
more » ... sive results of our method in real traffic images including high congestion, noise, clutter, snow, and rain containing remarkable cast shadows, bad illumination conditions and occlusions, taken from both scenes of outdoor highways and urban roads are presented.
doi:10.1109/icmv.2007.4469289 fatcat:q2sdxrp4rbg47bo664zioo7yga