A framework for background modelling and shadow suppression for moving object detection in complex wavelet domain

This paper describes a simple, robust and efficient framework for background subtraction and cast shadow suppression in complex wavelet domain. A background subtraction approach exploiting noise resilience capability of wavelet domain combined with local spatial coherence and median filter in the training stage is proposed. A novel shadow suppression scheme based on directional coefficients of Daubechies complex wavelet transform is introduced. The effectiveness of the proposed approach is demonstrated via qualitative and quantitative evaluation measures on both indoor and outdoor video sequences. The experimental results show that the proposed approach outperforms state-of-the-art methods.