PROJECT TITLE :

Saliency detection for stereoscopic images based on Depth confidence analysis and multiple cues fusion - 2016

ABSTRACT:

Stereoscopic perception is a vital half of human visual system that enables the brain to perceive depth. However, depth data has not been well explored in existing saliency detection models. In this letter, a novel saliency detection method for stereoscopic pictures is proposed. 1st, we propose a live to evaluate the reliability of depth map, and use it to scale back the influence of poor depth map on saliency detection. Then, the input image is represented as a graph, and therefore the depth data is introduced into graph construction. After that, a brand new definition of compactness using color and depth cues is put forward to compute the compactness saliency map. So as to compensate the detection errors of compactness saliency when the salient regions have similar appearances with background, foreground saliency map is calculated based mostly on depth-refined foreground seeds' selection (DRSS) mechanism and multiple cues contrast. Finally, these two saliency maps are integrated into a final saliency map through weighted-total method in line with their importance. Experiments on 2 publicly accessible stereo data sets demonstrate that the proposed method performs higher than alternative 10 state-of-the-art approaches.