Video Segmentation Based On Strong Target Constrained Video Saliency

Video segmentation often refers to the process of extracting the interest region from background according to the simple or complex features of the video.Computer vision algorithm has been widely applied to various fields.The video segmentation technology has an important influence on computer vision field,and the accuracy of segmentation results directly affect the high level processes,such as video understanding.A video segmentation method based on strong target constrained video saliency(STCVS)is proposed in this paper.In order to detect the salient region fast and effectively,the proposed STCVS is extracted based on the extension of image saliency by enforcing the salient region constrained with the location,scale and color model of the target.When computing the information of the target,the previous results are used to build estimated color model of the target.Furthermore,correcting the tracking result of the target by moving information is proposed,which has a good performance on calculation of target's location and scale.Besides,according to the results of STCVS,the super-pixel based spatial-temporal full-connected conditional random field method is given for video segmentation,where the super-pixel is regarded as basic unit instead of pixel due to the large amount of data in video,and the pairwise term of inter-frame is included for ensuring temporal and spatial continuity of video segmentation results.Compared with some state-of-art video segmentation methods on DAVIS data set,our proposed method performs outstandingly on accuracy,efficiency and robustness.