Target Tracking Method in Aerial Video Based on Saliency Fusion
Jie Han, Baolong Guo, Wei Sun · 2015
For the problem that when doing target tracking under dynamic background, the object extraction is susceptible to interference.Based on the static and dynamic saliency maps of video sequence, this paper presents a method of feature fusion.By calculating the weight for each of the significant area of the extracted static and dynamic saliency, based on human visual attention mechanism, the weighted comprehensive significant figure is get, so as to determine the status of the target.Several experiments are done by the mathod put forward in this paper and the experimental results show that the algorithm is able to solve the problem of susceptible to interference in target tracking, while ensuring robustness and meeting the real-time and accuracy needed.And the algorithm in this paper not only improves the real-time performance and robustness on the premise of guaranteeing the tracking accu racy, but also gives attribution to the field of target tracking.