Salient Region Detection Based on the Global Contrast Combining Background Measure for Indoor Robots

摘要

In this paper, we propose a new method of salient region detection for indoor robots, which integrate the background distribution into the primary saliency. Region roundness is proposed to describe the compactness of a region to measure background distribution more robustly. In order to validate the proposed method, several influential ones are compared on the DSD dataset. The results demonstrate that the proposed approach outperforms existing methods and is useful for indoor robots.