UAV detection in complex background with multi-scale feature fusion enhancement and channel-weight matching up-sampling

Abstract The reckless flight of unmanned aerial vehicle (UAV) seriously threatens the public and aviation safety. Due to their small size and unobvious features, it remains a great challenge for the current detection algorithms to detect UAV, especially in complex backgrounds with backlighting. To address these issues, the multiscale feature fusion enhancement strategy and channel-weight matching (CWM) rule are proposed in this paper. A multiscale feature fusion enhancement strategy is presented to capture the multi-scale contextual information, which not only suppresses information conflicts but also enhances feature extraction capabilities. Then, an up-sampling method based on CWM is designed to enhance the sensitivity of small object, which uses different up-sampling techniques based on the importance level of each feature channel. Finally, a feature refinement module for small object is designed to further enhance the characterization of their features. The ablation and comparative experiments are carried out on the self-made UAV dataset. Compared to the original YOLOv5 algorithm, the proposed method shows an increase of 3.6% in mAP0.5 and 2.8% in mAP0.5:0.95, respectively. Moreover, the comparative experiments are implemented on the VisDrone2019 dataset, and the results indicate that the mAP0.5 and mAP0.5:0.95 of the proposed method also increase by 4.2% and 1.6%, respectively.