Robust Salient Object Detection via Fusing Foreground and Background Priors

Abstract

Automatic salient object detection without any supervised labor tends to greatly enhance many computer vision tasks. This paper proposes a novel bottom-up salient object detection framework which considers both foreground and background priors in detecting process. First, a series of foreground seeds are extracted from an image based on surroundedness cue. Then, a foreground-corresponding saliency map is generated via ranking algorithm according to these seeds. In a similar way a series of background seeds are extracted and used for generating a background-corresponding saliency map. Finally, the two saliency maps are fused into one, and subsequently enhanced by geodesic refinement to derive the final saliency map. Extensive experimental evaluation demonstrates the effectiveness of our proposed framework against other outstanding methods.