Visual Detection and Tracking Based on Fusion Saliency
Xinxing Guo, Baolong Guo, Cheng Li, Jie Han · Journal of Physics Conference Series · 2018
In order to improve the ability of target tracking effectively, an improved MeanShift algorithm is proposed in this paper. The algorithm combines the saliency map from the computer and from the human vision through Kinect, so that it can obtain the fusion saliency. Then an image segmentation algorithm is adopted to get the target, which is modelled for an improved MeanShift tracking framework. Experimental results show that the algorithm can significantly improve the accuracy.