Spatio-Temporal Residual Attention Network for Satellite-Based Infrared Small Target Detection.
Saved in:
| Title: | Spatio-Temporal Residual Attention Network for Satellite-Based Infrared Small Target Detection. |
|---|---|
| Authors: | Chang, Yan1 (AUTHOR), Ma, Decao1 (AUTHOR) madecaoedu@163.com, Yang, Qisong1 (AUTHOR), Li, Shaopeng1 (AUTHOR), Zhang, Daqiao1 (AUTHOR) |
| Source: | Remote Sensing. Oct2025, Vol. 17 Issue 20, p3457. 20p. |
| Subjects: | Infrared technology, Remote sensing, Space vehicles, Applied sciences, Spatiotemporal processes, Electronic surveillance, Signal detection |
| Abstract: | Highlights: What are the main findings? A spatio-temporal detection framework is proposed for infrared small target detection in satellite video, which combines inter-frame residuals with spatial and temporal feature learning. The proposed method achieves superior detection accuracy and robustness compared with state-of-the-art approaches, particularly for tiny and dim targets in complex backgrounds. What is the implication of the main finding? The framework provides an effective solution for detecting small moving aerial targets from satellite infrared video, supporting reliable long-range monitoring. This study demonstrates the potential of integrating temporal consistency and multi-scale spatial features to advance real-world remote sensing applications. With the development of infrared remote sensing technology and the deployment of satellite constellations, infrared video from orbital platforms is playing an increasingly important role in airborne target surveillance. However, due to the limitations of remote sensing imaging, the aerial targets in such videos are often small in scale, low in contrast, and slow in movement, making them difficult to detect in complex backgrounds. In this paper, we propose a novel detection network that integrates inter-frame residual guidance with spatio-temporal feature enhancement to address the challenge of small object detection in infrared satellite video. This method first extracts residual features to highlight motion-sensitive regions, then uses a dual-branch structure to encode spatial semantics and temporal evolution, and then fuses them deeply through a multi-scale feature enhancement module. Extensive experiments show that this method outperforms mainstream methods in terms on various infrared small target video datasets, and has good robustness under low-signal-to-noise-ratio conditions. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? A spatio-temporal detection framework is proposed for infrared small target detection in satellite video, which combines inter-frame residuals with spatial and temporal feature learning. The proposed method achieves superior detection accuracy and robustness compared with state-of-the-art approaches, particularly for tiny and dim targets in complex backgrounds. What is the implication of the main finding? The framework provides an effective solution for detecting small moving aerial targets from satellite infrared video, supporting reliable long-range monitoring. This study demonstrates the potential of integrating temporal consistency and multi-scale spatial features to advance real-world remote sensing applications. With the development of infrared remote sensing technology and the deployment of satellite constellations, infrared video from orbital platforms is playing an increasingly important role in airborne target surveillance. However, due to the limitations of remote sensing imaging, the aerial targets in such videos are often small in scale, low in contrast, and slow in movement, making them difficult to detect in complex backgrounds. In this paper, we propose a novel detection network that integrates inter-frame residual guidance with spatio-temporal feature enhancement to address the challenge of small object detection in infrared satellite video. This method first extracts residual features to highlight motion-sensitive regions, then uses a dual-branch structure to encode spatial semantics and temporal evolution, and then fuses them deeply through a multi-scale feature enhancement module. Extensive experiments show that this method outperforms mainstream methods in terms on various infrared small target video datasets, and has good robustness under low-signal-to-noise-ratio conditions. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs17203457 |
