A Spatio-Temporal Attention Network With Multiframe Information for Infrared Small Target Detection
Infrared small target detection holds great potential for various applications, but also faces numerous challenges. Among these, detection algorithms for moving small targets are increasingly gaining attention. Most algorithms focus solely on extracting features from the spatial domain. However, thi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11113290/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Infrared small target detection holds great potential for various applications, but also faces numerous challenges. Among these, detection algorithms for moving small targets are increasingly gaining attention. Most algorithms focus solely on extracting features from the spatial domain. However, this approach often leads to suboptimal detection performance. While some methods attempt to incorporate temporal information during detection, nonlearning-based approaches are highly sensitive to noises and require manual parameter adjustments based on the input data. To tackle this problem, this article proposes a novel multiframe network called as a spatio-temporal attention network with multiframe information. This proposed method thinks of the infrared detection of moving small targets as the trajectory classification. First, the candidate targets are extracted by analyzing the spatial information of each image frame. The trajectories formed by candidate targets contain temporal information. The subsequent analysis of the temporal motion and appearance information serves to distinguish the real target from the background interference among the candidate targets. Concurrently, the coordinate attention block is integrated into the model to direct the algorithm to emphasize the local detail features of the target, thereby enhancing the processing capability of the temporal information. The experimental results on two public datasets demonstrate that the proposed method can substantially reduce the number of false alarm targets without significantly losing real targets. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |