Multi-Scale Enhanced Features Correlation Filters Learning With Dual Second-Order Difference for UAV Tracking

Currently, most Discriminative Correlation Filters (DCF) algorithms used for Unmanned Aerial Vehicle (UAV) target tracking primarily focus on improving the tracking model. However, in UAV tracking, the tracked targets are typically small in size and frequently undergo scale variations, making singular improvements to tracking models less effective. As a response to this challenge, we propose a novel feature preprocessing approach. Specifically, for the extracted Histogram of Oriented Gradients (HOG) and Color Names (CN) features, we simulate their transformations at different scales and electively enhance the target region features based on global features to obtain multi-scale enhanced features. By implementing these procedures, the tracker improves its ability to recognize targets and exhibits increased adaptability in challenging tracking scenarios. Furthermore, in contrast to the conventional approach used by most UAV algorithms, which unidirectionally incorporate historical filters into model updates to prevent filter divergence, we introduce dual second-order difference terms that correspond to features and filters. This integration enables a more effective fusion of historical information with current frame data, thereby enhancing the robustness of the filtering process. Extensive experiments are conducted to evaluate the proposed tracker against other state-of-the-art trackers using the DTB70, UAV123@10fps, and UAVDT datasets. The experimental results affirm the effectiveness of our approach.