The AAV Tracking: Fusion and Adversarial of Global and Local Information

The widespread application of autonomous aerial vehicles (AAVs) in various fields has driven the development of target tracking based on AAV perspectives. Among the existing tracking algorithms, tracking by detection performs well, which depends heavily on the robustness of the object detection and re-identification algorithms. The images obtained from the perspective of drones have complex backgrounds and small image sizes, making tracking tasks more difficult. We introduce the parallel space and channel attention module to optimize the object detection algorithm, exploring compelling spatial and channel dimensions features. We propose the channel-spatial fully connected information extraction module, which explores the connections between pixels from a spatial perspective and considers the relationships between feature maps from a channel perspective, compensating for the shortcomings of convolutional networks in extracting global features. To obtain more discriminative feature descriptions, we design the global-local-residual feature fusion module that divides the image into global and local parts and gets the difference between local information and other information, which helps with data correlation and label matching. Experiments show that our method improves the mAP by 0.4% and AP by 2.1% in the object detection task. In the re-identification task, top-1 accuracy is improved by 5.3% and mAP by 11.3%.