Video saliency detection based on temporal difference and pixel gradient

Even though temporal information matters for the quality of video saliency detection, many problems such as bad performance in time-space coherence and edge continuity still face present network frameworks. In response to these problems, this paper designs a full convolutional neural network, which integrates temporal differential and pixel gradient to fine tune the edges of targets. Meanwhile, the changes of pixel gradients of original images are used to recursively improve the continuity of target edges and details of central areas. The method presented in the paper has been tested with two available public datasets and its effectiveness been proved after it being compared with 6 other widely accepted methods.