Spatio-temporal saliency detection using objectness measure

Spatio-temporal saliency detection has gradually gained much attention in various computer vision applications such as intelligent video advertising and visual tracking. In this paper, we present a new approach based on the spatial and temporal information of the input video frame which aims to find the similar salient objects is proposed. First, objectness measure is performed to highlight the regions that may contain the object of interest. Then, for each candidate, newly proposed motion distinctiveness cues and static features including contrast measure and spatial distance are used to compute saliency maps. Experiments over two widely benchmark datasets, using several evaluation metrics such as mean absolute error, F score and area under the ROC curve measures, show the efficiency of our saliency approach compared to recent state-of-the-art methods. More interestingly, our attended scenes locations are coherent with the ground truth video frames. On SegTrack v2 and Fukuchi datasets, our proposed method yielded an overall mean absolute error, respectively, of 0.0669 and 0.0794. These results indicate the potential of our proposed framework in detecting motion salient objects.