RMT-YOLOv9s: An Infrared Small Target Detection Method Based on UAV Remote Sensing Images

Abstract

Unmanned aerial vehicles (UAVs) and infrared imaging technology have numerous applications in civilian fields. To address the issues of low accuracy resulting from complex ground backgrounds, small target size, and limited target features in UAV remote sensing infrared image target detection, we use the YOLOv9s model and the latest retentive networks meet vision transformers (RMTs) technology and propose the RMT-YOLOv9s model for infrared small target detection. First, a convolutional neural network (CNN)-RMT-based backbone is proposed by incorporating the RMT model into the backbone network of YOLOv9s, which extracts both local and global features for small target detection. Then, an improved neck multiscale feature-fusion network RMTELAN-PANet is designed using the novel convolutional RMTELAN module proposed in this letter, which can better capture and use semantic information from feature maps. Finally, efficient multiscale attention (EMA) attention module and upsampling Dysample module are integrated into RMTELAN-PANet to further improve the feature information of small targets. Experiments on the HIT-UAV dataset show that RMT-YOLOv9s outperforms other popular methods in infrared small target detection.