Complex wavelet based moving object segmentation using approximate median filter based method for video surveillance

This paper proposes complex wavelet-based moving object segmentation using approximate median filter based method. The proposed method is well capable of dealing with the drawbacks such as ghosts, shadows and noise present in other spatial domain methods available in literature. The performance of the proposed method is evaluated and compared with other standard spatial domain methods. The various performance measures used for comparison include RFAM (relative foreground area measure), MP (misclassification penalty), RPM (relative position based measure), NCC (normalized cross correlation) and the various methods are tested on standard Pets dataset. Finally, based on performance analysis it is observed that the proposed method in complex wavelet domain is performing better in comparison to other methods as presented in the paper.