Shadow detection based on combinations of HSV color space and orthogonal transformation in surveillance videos

摘要

Shadow removing is an important issue in performance of intelligent transportation system. In this paper, a synthetic shadow detection algorithm using combination of orthogonal transformation and HSV color space is proposed. In this algorithm, orthogonal transformation and HSV color space are applied to improve the performance of shadow detection. At first, the current and background images are transferred from RGB color space to HSV color space, then using combination of orthogonal transformation and shadow color feature in HSV color space, the shadow is detected in the image blocks. Our proposed algorithm is evaluated on a real and operation videos. The obtained results by our algorithm demonstrate the efficiently and effectiveness of this algorithm in intelligent transportation system application.