Prior fusion based salient object detection

Abstract

Object level saliency detection is useful for many content-based computer vision tasks. In this letter, we present a novel bottom-up salient object detection approach by exploiting contrast, and center priors. In the past, the algorithms of saliency detection are generally based on the contrast of the priors, but only using a prior that there are still many problems, if not uniformly outstanding goals. Currently, a lot of work introduce center prior to significant target detection. However, the center prior is very sensitive to the position of the target that once deviation from the center, the center prior will no longer be established. In this paper, we explore the surroundedness cue for saliency detection. The essence of surroundedness is the enclosure topological relationship between the figure and the ground, which is achieved by random threshold color channel of the image. in order to enhance robustness and effectiveness of the center prior. Then fusion contrast prior and new center prior to generate a new saliency map.