LightMaskMamba: A Near-Ground Remote Sensing Object Detection Network with Visible–Infrared Fusion
Remote Sensing · 19.11.2026 · 18 (22) · 3985
DOI: 10.3390/rs18223985 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.11.2026. Verfasst von Kaihua Liang und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Technologies Research and Development Program of Guangzhou Municipality, the Guangdong Science and Technology Program, the Guangdong High-Level Talents Special Program.
Abstract (Originalsprache)
Visible–infrared fusion is a main route to all-weather object extraction in near-ground remote sensing, but single-band RGB remains unstable under occlusion, clutter, and low light and illumination variation. This study presents LightMaskMamba, a lightweight visible–infrared object detection network for near-ground remote sensing. Public benchmarks test fusion quality across scenes, and the self-built near-ground wampee field dataset is for deployment-oriented field validation. The core of the network is a lightweight mask-guided Mamba fusion architecture. Its key module, the Lightweight Mask Mamba Fusion Block (LMMFB), uses an object-related mask to drive shallow-to-deep VIS–NIR feature fusion, focuses computation on object regions, and reduces scan redundancy. Dual-band detection therefore stays light enough to run at the edge. On the self-built wampee dataset, LightMaskMamba-v11s reaches 97.4% mAP50 and 52.0% mAP50:95. Relative to single-band YOLOv11s, mAP50 is 2.3 and 4.6 percentage points higher on IR and RGB. Parameters rise by 3.7M, from 8.8M to 12.5M. The same model is likewise effective in detection accuracy, and lighter, on public multimodal object-detection datasets. On a Jetson Orin NX Super, TensorRT INT8 mixed-precision inference reaches about 17.3 FPS, or 58 ms per image.
Förderung
- the Key Technologies Research and Development Program of Guangzhou Municipality
- the Guangdong Science and Technology Program
- the Guangdong High-Level Talents Special Program
- the Research Fund of Guangzhou University of Software
- the Joint Fund Project of Dalian Minzu University and Tibet Agricultural and Animal Husbandry University
Zitieren
APA
Liang, K., Wang, Y., Li, C., He, Z., Chen, Z., Ye, R., & Li, J. (2026). LightMaskMamba: A Near-Ground Remote Sensing Object Detection Network with Visible–Infrared Fusion. Remote Sensing, 18(22), 3985. https://doi.org/10.3390/rs18223985
Vancouver
Liang K, Wang Y, Li C, He Z, Chen Z, Ye R, et al. LightMaskMamba: A Near-Ground Remote Sensing Object Detection Network with Visible–Infrared Fusion. Remote Sensing. 2026;18(22):3985. doi:10.3390/rs18223985
BibTeX
@article{Liang2026,
author = {Liang, Kaihua and Wang, Yuzhe and Li, Chenming and He, Zhipeng and Chen, Zhongmin and Ye, Ruixing and Li, Jiehao},
title = {LightMaskMamba: A Near-Ground Remote Sensing Object Detection Network with Visible–Infrared Fusion},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {22},
pages = {3985},
doi = {10.3390/rs18223985}
}
EUVIMED