A Robust Background Subtraction Approach Based on Daubechies Complex Wavelet Transform

This paper describes a simple and robust approach for background subtraction in Daubechies 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. The effectiveness of the proposed approach is demonstrated via qualitative and quantitative evaluation measures on both indoor and outdoor video sequences. The experimental results illustrate that the proposed approach outperforms state-of-the-art methods.