Salient region detection for stereoscopic images

Abstract

In this paper, we propose an effective saliency model, which combines region-level depth, color and spatial information, to detect salient regions in stereoscopic images. Based on region segmentation results of stereoscopic images, depth contrast, depth weighted color contrast, and spatial compactness of color distribution are measured for each region, and combined to generate the region-level saliency map. Experimental results on a public stereoscopic image dataset with ground truths of salient objects demonstrate that the proposed saliency model outperforms the state-of-the-art saliency models.