Abstract: The frequent illegal use of civilian low altitude small unmanned aerial vehicles poses a serious threat to the harmonious development of the country and society. In response to the problems of missed detection, false detection, and low detection accuracy in visible light based small target detection of unmanned aerial vehicles, this paper proposes the YOLO SCAT (YOLO SCConv ATT) algorithm model to reconstruct the ELAN structure and reduce redundant spatial and channel features; At the same time, the attention mechanism CBAM is introduced to enhance feature extraction in space and channels during training, improving the detection accuracy of the model. The experiment shows that the YOLO-SCAT model has high accuracy, recall, F1 score mAP@0.5 The YOLO-SCAT model achieves 94.4%, 94.4%, 94.4%, 94.7%, and 52.9% for mAP @ 0.5:0.95, indicating that it improves the detection and recognition ability of small targets in complex visible light scenes, and can better meet the practical needs of anti drone systems.