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

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, impressive 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.