Small Target Detection Network Based on Unmanned Aerial Vehicle Infrared Imaging Sensor
Year: 2026
Type: article
Abstract: Infrared imaging sensors play a crucial role in unmanned aerial vehicle imagery due to their passive imaging capability and robustness under low-light conditions. The small pixels of distant targets result in sparse feature representation, which can easily lead to low detection rates. This study proposes a small target detection network, namely, infrared small-target RTDETR (IST-RTDETR). A novel attention mechanism, namely, frequency mamba-like linear attention, has been designed, which can capture local detailed features in detail and fully model global dependencies at long distances, thereby significantly enhancing the network’s ability to extract key information of small targets in complex backgrounds. A dynamic adaptive feature fusion module is proposed to achieve adaptive integration of multiscale local features and global features, further enhancing the feature expression and fusion effect of the network, and further improving the overall detection performance. The experimental results on the HIT-UAV dataset show that the detection accuracy of IST-RTDETR is superior to mainstream object detection methods. Compared with RT-DETR, IST-RTDETR increased$\text{mAP}_{50}$and$\text{mAP}_{s}$by 1.5% and 2.3%, respectively. This network also achieves an effective balance between computational complexity and detection accuracy.
Source: IEEE Sensors Letters
Authors: Li Ang, Zhu Fuyang, Raseeda Hamzah
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,645
OpenAlex ID: W7204789148