Structured Saliency Fusion Based on Dempster–Shafer Theory

Visual saliency has been widely used in many applications. However, the performance of an individual saliency detection method varies with the different images. Integrating multiple methods together could compensate this shortcoming, and thus is expected to improve the performance of saliency detection. In this paper, we present an unsupervised Dempster-Shafer Theory (DST) based saliency fusion framework. DST simulates the similar reasoning logic with humans to make decision analysis, and has been proved a suitable method for data fusion. Inspired by this, our framework formalizes the saliency fusion as a statistics inference process, considering the results from several saliency methods to accomplish the fusion task. Furthermore, the proposed framework can flexibly incorporate a variety of inherent structured priors within the images (e.g., clusters and saliency voting) when leveraging the fusion rule of DST. Therefore, it is more close to the fusion mechanism. Experimental results on two benchmark datasets demonstrate the effectiveness and robustness of our framework.