GMF-Net: A Gaussian-Matched Fusion Network for Weak Small Object Detection in Satellite Laser Ranging Imagery
文献类型：期刊论文
| 作者 | Zhu, Wei2,3; Gong, Weiming2,3; Wang, Yong1; Zhang, Yi2; Hu, Jinlong2 |
| 刊名 | SENSORS
 |
| 出版日期 | 2026-01-08 |
| 卷号 | 26期号:2页码:20 |
| 关键词 | satellite laser ranging (SLR) small object detection lightweight network GMF-Net Gaussian-matched convolution |
| DOI | 10.3390/s26020407 |
| 通讯作者 | Hu, Jinlong(hujinlong23@mails.ucas.ac.cn) |
| 英文摘要 | Detecting small objects in Satellite Laser Ranging (SLR) CCD images is critical yet challenging due to low signal-to-noise ratios and complex backgrounds. Existing frameworks often suffer from high computational costs and insufficient feature extraction capabilities for such tiny targets. To address these issues, we propose the Gaussian-Matched Fusion Network (GMF-Net), a lightweight and high-precision detector tailored for SLR scenarios. The core scientific innovation lies in the Gaussian-Matched Convolution (GMConv) module. Unlike standard convolutions, GMConv is theoretically grounded in the physical Gaussian energy distribution of SLR targets. It employs multi-directional heterogeneous sampling to precisely match target energy decay, enhancing central feature response while suppressing background noise. Additionally, we incorporate a Cross-Stage Partial Pyramidal Convolution (CSPPC) to reduce parameter redundancy and a Cross-Feature Attention (CFA) module to bridge multi-scale features. To validate the method, we constructed the first dedicated SLR-CCD dataset. Experimental results show that GMF-Net achieves an mAP@50 of 93.1% and mAP@50-95 of 52.4%. Compared to baseline models, parameters are reduced by 26.6% (to 2.2 M) with a 27.4% reduction in computational load, demonstrating a superior balance between accuracy and efficiency for automated SLR systems. |
| WOS研究方向 | Chemistry ; Engineering ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:001671415800001 |
| 出版者 | MDPI |
| 源URL | [http://ir.xao.ac.cn/handle/45760611-7/8526]  |
| 专题 | 光学天文与技术应用研究室_光学天文技术研究团组 |
| 通讯作者 | Hu, Jinlong |
| 作者单位 | 1.Chinese Acad Sci, Xinjiang Astron Observ, Urumqi 830011, Peoples R China 2.China Earthquake Adm, Inst Seismol, Wuhan 430071, Peoples R China 3.Hubei Earthquake Agcy, Hubei Key Lab Earthquake Early Warning, Wuhan 430071, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhu, Wei,Gong, Weiming,Wang, Yong,et al. GMF-Net: A Gaussian-Matched Fusion Network for Weak Small Object Detection in Satellite Laser Ranging Imagery[J]. SENSORS,2026,26(2):20. |
| APA | Zhu, Wei,Gong, Weiming,Wang, Yong,Zhang, Yi,&Hu, Jinlong.(2026).GMF-Net: A Gaussian-Matched Fusion Network for Weak Small Object Detection in Satellite Laser Ranging Imagery.SENSORS,26(2),20. |
| MLA | Zhu, Wei,et al."GMF-Net: A Gaussian-Matched Fusion Network for Weak Small Object Detection in Satellite Laser Ranging Imagery".SENSORS 26.2(2026):20. |
入库方式： OAI收割
来源：新疆天文台
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。