Visual object tracking is one of the most attractive issue in computer vision. Recently, deep neural network has beenwidely developed in object tracking and showing great accuracy. In general, the accuracy of tracking task decreasesdramatically when the background becomes complex or occluded. Here, we propose an end-to-end lightweight siameseconvolution neural network to achieve fast and robust target tracking especially for infrared target. The network structurereplaces the hand-crafted features by the multi-layers deep convolution features of the target, so that higher precision canbe achieved. Specifically, object location is updated in every frame by refreshing a response-map. However, the successrate of tracking task decreases dramatically when the background becomes complex or occluded. Consequently, a simpleand robust anti-occlusion tracking method is presented. The tracking accuracy is evaluated during tracking process bycomputing the tracking confidence parameters. The parameters are composed of two parts: target confusion degreewhich indicates the degree of background interference and target occlusion degree which indicates the degree of targetocclusion. Once the target is occluded, the location of the target object is corrected immediately. Experimental resultsdemonstrate that the proposed framework achieves state-of-the-art performance on the popular OTB50 and OTB100benchmarks.
展开▼