Learning channel-selective and aberrance repressed correlation filter with memory model for unmanned aerial vehicle object tracking

To ensure that computers can accomplish specific tasks intelligently and autonomously, it is common to introduce more knowledge into artificial intelligence (AI) technology as prior information, by imitating the structure and mindset of the human brain. Currently, unmanned aerial vehicle (UAV) tracking plays an important role in military and civilian fields. However, robust and accurate UAV tracking remains a demanding task, due to limited computing capability, unanticipated object appearance variations, and a volatile environment. In this paper, inspired by the memory mechanism and cognitive process in the human brain, and considering the computing resources of the platform, a novel tracking method based on Discriminative Correlation Filter (DCF) based trackers and memory model is proposed, by introducing dynamic feature-channel weight and aberrance repressed regularization into the loss function, and by adding an additional historical model retrieval module. Specifically, the feature-channel weight integrated into the spatial regularization (SR) enables the filter to select features. The aberrance repressed regularization provides potential interference information to the tracker and is advantageous in suppressing the aberrances caused by both background clutter and appearance changes of the target. By optimizing the aforementioned two jointly, the proposed tracker could restrain the potential distractors, and train a robust filter simultaneously by focusing on more reliable features. Furthermore, the overall loss function could be optimized with the Alternative Direction Method of Multipliers (ADMM) method, thereby improving the calculation efficiency of the algorithm. Meanwhile, with the historical model retrieval module, the tracker is encouraged to adopt some historical models of past video frames to update the tracker, and it is also incentivized to make full use of the historical information to construct a more reliable target appearance representation. By evaluating the method on two challenging UAV benchmarks, the results prove that this tracker shows superior performance compared with most other advanced tracking algorithms.