Infrared small target detection improved with selective attention network
SANet: Selective Attention Network for Infrared Small Target Detection
Computer Vision and Pattern Recognition
Summary
Detecting tiny and dim targets in infrared images is tricky because they blend into complicated backgrounds. The authors developed a new method called SANet that uses special attention mechanisms to better spot these targets while reducing false alarms. They combine different types of image filters and selectively focus on important regions to separate targets from background noise. Tests show SANet performs better than other methods on several public datasets.
What this means in practice
- •For maritime security teams: Enhance detection of small and dim objects in complex sea environments using infrared sensors for improved surveillance capability.
- •For military search and rescue units: Improve accuracy and reduce false alarms in locating survivors or threats using infrared small target detection technology in diverse terrains.
Authors
Yingmei Zhang, Wangtao Bao, Qin Xiao, Yong Yang, Weiguo Wan, Yitao Luo, Xueting Zou, Lei Zhang
Abstract
Infrared small target detection aims to accurately identify and locate dim targets in complex backgrounds and supports applications such as maritime surveillance and military search and rescue. However, the small size and weak contrast of infrared targets make it difficult to balance detection accuracy and false alarms. This paper proposes a selective attention network (SANet) for infrared small target detection. A dual-path semantic-aware module combines standard and pinwheel-shaped convolutions to preserve local spatial consistency and capture broader contextual information. Spatial and channel attention further refine the features and improve target-background discrimination. To address the limitations of static skip connections in U-Net, a selective attention fusion module adaptively integrates features across scales using spatially varying weights. It selectively enhances salient regions and improves discrimination between true targets and false alarms. Experiments on three public benchmarks, NUAA-SIRST, IRSTD-1K, and NUDT-SIRST, show that SANet achieves competitive performance in intersection over union (IoU), normalized IoU, detection probability, and false alarm rate. Its IoU exceeds that of the second-best method by 1.93, 4.32, and 2.21 percentage points, respectively. These results support the effectiveness of SANet in dim-target perception, discriminative feature representation, and background suppression.