Shadow Detection for Vehicles by Locating the Object-Shadow Boundary

A.W.K. So, K.-Y.K. Wong, R.H.Y. Chung, and F.Y.L. Chin (PRC)


Shadow detection, shadow identification, object detection, video segmentation


We introduce in this paper a shadow detection method for vehicles in traffic video sequences. Our method approxi mates the boundary between vehicles and their associated shadows by one or more straight lines. These lines are located in the image by exploiting both local information (e.g. statistics in intensity differences) and global informa tion (e.g. principal edge directions). The proposed method does not assume a particular lighting condition, and re quires no human interaction nor parameter training. Ex periments on practical real-world traffic video sequences demonstrate that our method is simple, robust and efficient under traffic scenes with different lighting conditions. Ac curate positioning of target vehicles is thus achieved even in the presence of cast shadows.

Important Links:

Go Back