High-performance UAVs visual tracking based on siamese network

In the process of unmanned aerial vehicles (UAVs) object tracking, the tracking object is lost due to many problems such as occlusion and fast motion. In this paper, based on the SiamRPN algorithm, a UAV object tracking algorithm that optimizes the semantic information of cyberspace, channel feature information and strengthens the selection of bounding boxes, is proposed. Since the traditional SiamRPN method does not consider remote context information, the calculation and selection of bounding boxes need to be improved. Therefore, (1) we design a convolutional attention module to enhance the weighting of feature spatial location and feature channels. (2) We also add a multi-spectral channel attention module to the search branch of the network to further solve remote dependency problems of the network and effectively understand different UAVs tracking scenes. Finally, we use the distance intersection over union to predict the bounding box, and the accurate prediction bounding box is regressed. The experimental results show that the algorithm has strong robustness and accuracy in many scenes.