Infrared image UAV target detection algorithm based on IDOU-YOLO

Small, low-altitude small unmanned aerial vehicles (UAVs) frequently invade sensitive areas, posing a serious threat to national and social security. There are problems such as high missed detection rate and insufficient detection accuracy for UAV target detection based on thermal imaging. This paper proposes the IDOU-YOLO (Infrared Detection Of UAV-YOLO) algorithm model. A multi-scale merged feature pyramid mechanism is constructed to fully explore the feature space information, focuses on scale information fusion and the rich information representation ability of the model, and enhances target detection ability. The bounding box loss function SIOU is introduced to improve the detection accuracy of the model and accelerates the convergence speed of the model in the training process. The experimental results show that the precision, recall, F₁ score, mAP@0.5 and mAP@0.5 0.95 achieved 99.2%, 96.3%, 97.7%, 98.4%, and 70.2%, indicating that the IDOU-YOLO algorithm model has significant advantages and application potential in thermal imaging based UAV target detection.