Video object segmentation and its salient motion detection using adaptive background generation
T.K. Kim, Jaehyun Im, Joonki Paik · Electronics Letters · 2009
Video object segmentation often fails when the background and foreground contain a similar distribution of colours. Proposed is a novel image segmentation algorithm to detect salient motion under a complex environment by combining temporal difference and background generation. Experimental results show that the proposed algorithm provides a twice higher matching ratio than the conventional Gaussian mixture-based approaches under various conditions.