Multiple feature distinctions based saliency flow model

Abstract

Salient object detection has become a primary focus of research in computer vision, since it bridges the cognitive process in scene understanding and the distinction in the minute object details. In the current state-of-the-art literatures on salient object detection, the focus is in finding one or several more discriminative features to segment the salient object from the background. However, in the analysis of complex scenes, most techniques are challenged by noise, granularity and regions in the scene image with similar pixel intensities. Inspired by the feature integration theory in cognitive psychology, it is noticed that the salient objects can be associated with the image regions that are consistently distinct in most of the feature spaces. Base on this point, the feature distinctions are computed in each feature space respectively, and a saliency flow model is proposed to formulate the process of the saliency spread directly. Both low level and mid-level features are involved. Finally, the saliency map is obtained through fusing the feature distinction maps with the tuned weights after a post-processing. The consistent feature distinctions are free from the specific elaborate features and represent higher robustness in the complex scenes. This also benefits our model. Extensive experiments on six public benchmark databases demonstrate the robustness and the superior performance of the proposed method.