Coherency Based Spatio-Temporal Saliency Detection for Video Object Segmentation

Extracting moving and salient objects from videos is important for many applications like surveillance and video retargeting. In this paper we use spatial and temporal coherency information to segment salient objects in videos. While many methods use motion information from videos, they do not exploit coherency information which has the potential to give more accurate saliency maps. Spatial coherency maps identify regions belonging to regular objects, while temporal coherency maps identify regions with high coherent motion. The two coherency maps are combined to obtain the final spatio-temporal map identifying salient regions. Experimental results on public datasets show that our method outperforms two competing methods in segmenting moving objects from videos.