航天遥感图像智能处理与分析专刊

基于光照控制的月球表面精确着陆点定位算法

  • 舒世灏 ,
  • 孟偲 ,
  • 白相志 ,
  • 史振威
展开
  • 1.北京航空航天大学 宇航学院 智能科学与技术系,北京 102206
    2.空间飞行器设计优化与动态模拟技术教育部重点实验室,北京 102206
    3.北航-威睛AI+计算光学联合实验室,北京 102206
E-mail: tsai@buaa.edu.cn

收稿日期: 2025-10-10

  修回日期: 2025-11-28

  录用日期: 2025-12-29

  网络出版日期: 2026-01-19

基金资助

北京市自然基金联合重点项目(L258070)

Precise lunar landing site localization algorithm based on illumination control

  • Shihao SHU ,
  • Cai MENG ,
  • Xiangzhi BAI ,
  • Zhenwei SHI
Expand
  • 1.Department of Aerospace Intelligent Science and Technology,School of Astronautics,Beihang University,Beijing 102206,China
    2.Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technology,Ministry of Education,Beijing 102206,China
    3.Beihang - Vision AI + Computational Optics Joint Laboratory,Beijing 102206,China
E-mail: tsai@buaa.edu.cn

Received date: 2025-10-10

  Revised date: 2025-11-28

  Accepted date: 2025-12-29

  Online published: 2026-01-19

Supported by

Joint Key Project of Beijing Natural Science Foundation(L258070)

摘要

月球表面的光照变化对航天器着陆点定位带来了巨大挑战。传统的图像处理技术,如直方图均衡化和基于Retinex的方法,无法适应月球表面多变的光照环境。提出了一种融合光照控制算法LomFormer (Light on Moon)的着陆点定位流程,LomFormer算法基于Transformer,旨在将某一光照条件下的地外天体表面图像控制为另一光照角度,以解决基于视觉的着陆点定位流程中,月面遥感图像和着陆相机图像可能存在的光照不一致而导致无法匹配的问题。为对该模型进行训练,基于月表真实高程图数据进行多光照角度渲染,以生成多角度光照月表数据集。通过训练和验证得知,所提方法在真实数据中表现出良好的性能,有效增强了月表匹配的精度,且在不同光照条件下表现出强大的鲁棒性。该研究为解决航天器着陆点定位中的光照挑战提供了新的角度,并为未来的自主行星探测任务中的匹配建图任务提出了新的思路。

本文引用格式

舒世灏 , 孟偲 , 白相志 , 史振威 . 基于光照控制的月球表面精确着陆点定位算法[J]. 航空学报, 2026 , 47(10) : 532874 -532874 . DOI: 10.7527/S1000-6893.2025.32874

Abstract

The significant illumination variations on the lunar surface pose a substantial challenge to spacecraft landing site localization. Traditional image processing techniques, such as histogram equalization and Retinex-based methods, struggle to adapt to the highly variable lighting conditions prevalent on planetary surfaces. To address the issue of illumination inconsistency between orbital remote sensing images and descent camera images-which often leads to matching failures in vision-based landing site localization pipelines—a novel localization framework that integrates a dedicated illumination control algorithm named LomFormer (Light on Moon) is proposed. Based on a Transformer architecture, LomFormer is designed to actively control the illumination angle in planetary surface images, effectively transforming an image captured under one lighting condition to appear as if it were taken under another. For model training, a multi-angle illumination dataset of the lunar surface was generated by rendering images based on real lunar Digital Elevation Model (DEM) data under various lighting azimuths and elevations. Training and validation results demonstrate that the proposed method achieves promising performance on real data, significantly enhancing the accuracy of lunar image matching and exhibiting strong robustness across diverse illumination scenarios. This research provides a novel perspective on tackling illumination-related challenges in spacecraft landing site localization and introduces a new paradigm for mapping and localization tasks in future autonomous planetary exploration missions.

参考文献

[1] PIZER S M, AMBURN E P, AUSTIN J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vision, Graphics, and Image Processing198739(3): 355-368.
[2] JOBSON D J, RAHMAN Z, WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing19976(7): 965-976.
[3] ZHANG Q W L, YANG M H, LI Q L, et al. Lunar farside volcanism 2.8 billion years ago from Chang’e-6 basalts[J]. Nature2025643(8071): 356-360.
[4] CUI Z X, YANG Q, ZHANG Y Q, et al. A sample of the Moon’s far side retrieved by Chang’e-6 contains 2.83-billion-year-old basalt[J]. Science2024386(6728): 1395-1399.
[5] LIU D Y, YE Z, XU Y S, et al. A mismatch removal method based on global constraint and local geometry preservation for lunar orbiter images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing202417: 10221-10236.
[6] LI X J, YUE Z Y, PENG M, et al. Characterization of lobate scarps at the western rim of the Apollo basin using high-resolution DEMs generated using generative adversarial network (GAN) based approach[J]. Icarus2025435: 116562.
[7] GOU S, YUE Z Y, LIN Y T, et al. Thin basaltic regolith at the Chang’e-6 landing site[J]. Earth and Planetary Science Letters2025655: 119266.
[8] 彭齐浩, 赵腾起, 刘传凯, 等. 一种鲁棒的月面宽基线图像特征匹配方法[J]. 光学学报202343(24): 2410001.
  PENG Q H, ZHAO T Q, LIU C K, et al. A robust feature matching method for wide-baseline lunar images[J]. Acta Optica Sinica202343(24): 2410001 (in Chinese).
[9] 邸凯昌, 刘召芹, 刘斌, 等. 多源数据的嫦娥四号着陆点定位[J]. 遥感学报201923(1): 177-184.
  DI K C, LIU Z Q, LIU B, et al. Chang’e-4 lander localization based on multi-source data[J]. Journal of Remote Sensing201923(1): 177-184 (in Chinese).
[10] 刘传凯, 王沼翔, 雷俊雄, 等. 基于松弛极线约束的月面复杂仿射变换图像匹配方法[J]. 航空学报202445(2): 328659.
  LIU C K, WANG Z X, LEI J X, et al. An epipolar relaxation constrained matching algorithm of large-affined images for lunar rover with large span distance in a single movement[J]. Acta Aeronautica et Astronautica Sinica202445(2): 328659 (in Chinese).
[11] 王镓, 吴伟仁, 李剑, 等. 基于视觉的嫦娥四号探测器着陆点定位[J]. 中国科学: 技术科学202050(1): 41-53.
  WANG J, WU W R, LI J, et al. Vision based Chang’e-4 landing point localization[J]. Scientia Sinica (Technologica)202050(1): 41-53 (in Chinese).
[12] 王镓, 李达飞, 何锡明, 等. 基于多源影像的“祝融号”火星车高精度定位[J]. 深空探测学报20229(1): 62-71.
  WANG J, LI D F, HE X M, et al. High precision localization of Zhurong rover based on multi-source images[J]. Journal of Deep Space Exploration20229(1): 62-71 (in Chinese).
[13] LIU J J, REN X, YAN W, et al. Descent trajectory reconstruction and landing site positioning of Chang’e-4 on the lunar farside[J]. Nature Communications201910: 4229.
[14] CHEN H, HU X Y, GL?SER P, et al. CNN-based large area pixel-resolution topography retrieval from single-view LROC NAC images constrained with SLDEM[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing202215: 9398-9416.
[15] 陈泽宇, 李兆津, 吴波, 等. 基于多视单目影像光度法的月球南极像素级三维重建[J]. 遥感学报202529(2): 415-428.
  CHEN Z Y, LI Z J, WU B, et al. Multi-view photoclinometry from monocular images for pixel-wise 3D mapping of the lunar South Pole region[J]. National Remote Sensing Bulletin202529(2): 415-428 (in Chinese).
[16] CHEN C, YE Z, XU Y S, et al. Large-scale block bundle adjustment of LROC NAC images for lunar south pole mapping based on topographic constraint[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing202417: 2731-2746.
[17] 焦春林, 高满屯, 史仪凯. 基于立体视觉的3D地形拼接[J]. 计算机工程与应用200844(23): 206-208.
  JIAO C L, GAO M T, SHI Y K. 3D terrain registration based on stereo vision[J]. Computer Engineering and Applications200844(23): 206-208 (in Chinese).
[18] LI Y, ZENG Y Y. Lunar image matching based on impact crater morphology and distribution for landing localization[C]∥IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE Press, 2024: 6146-6149.
[19] 王镓, 辛鑫, 万文辉, 等. 基于多源影像的探测器月面着陆点定位与精度验证[J]. 空间科学学报202141(2): 320-328.
  WANG J, XIN X, WAN W H, et al. Location and accuracy validation of lunar landing point based on multi-source images[J]. Chinese Journal of Space Science202141(2): 320-328 (in Chinese).
[20] COLTUC D, BOLON P, CHASSERY J M. Exact histogram specification[J]. IEEE Transactions on Image Processing200615(5): 1143-1152.
[21] CHEN H T, WANG Y H, GUO T Y, et al. Pre-trained image processing transformer[C]∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 12294-12305.
[22] LI Y W, FAN Y C, XIANG X Y, et al. Efficient and explicit modelling of image hierarchies for image restoration[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 18278-18289.
[23] ZHANG J L, ZHANG Y L, GU J J, et al. Accurate image restoration with attention retractable transformer[EB/OL]. arXiv preprint2210.01427, 2022.
[24] ZAMIR S W, ARORA A, KHAN S, et al. Restormer: Efficient transformer for high-resolution image restoration[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 5718-5729.
[25] LIANG J Y, CAO J Z, SUN G L, et al. SwinIR: Image restoration using swin transformer[C]∥2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Piscataway: IEEE Press, 2021: 1833-1844.
[26] GUO H, LI J M, DAI T, et al. MambaIR: A simple baseline forImage restoration withState-space model[C]∥Computer Vision-ECCV 2024. Cham: Springer, 2025: 222-241.
[27] GUO H, GUO Y, ZHA Y H, et al. MambaIRv2: Attentive state space restoration[EB/OL]. arXiv preprint2411.15269, 2024.
[28] CAI Y H, LIN J, LIN Z D, et al. MST++: Multi-stage spectral-wise transformer for efficient spectral reconstruction[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2022: 744-754.
[29] ZHANG L, LANG Z Q, WANG P, et al. Pixel-aware deep function-mixture network for spectral super-resolution[J]. Proceedings of the AAAI Conference on Artificial Intelligence202034(7): 12821-12828.
[30] XIONG Z W, SHI Z, LI H Q, et al. HSCNN: CNN-based hyperspectral image recovery from spectrally undersampled projections[C]∥2017 IEEE International Conference on Computer Vision Workshops (ICCVW). Piscataway: IEEE Press, 2018: 518-525.
[31] SHI Z, CHEN C, XIONG Z W, et al. HSCNN+: Advanced CNN-based hyperspectral recovery from RGB images[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2018: 939-947.
[32] CAI Y H, BIAN H, LIN J, et al. Retinexformer: One-stage retinex-based transformer for low-light image enhancement[C]∥2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2024: 12470-12479.
[33] ZHANG Y H, GUO X J, MA J Y, et al. Beyond brightening low-light images[J]. International Journal of Computer Vision2021129(4): 1013-1037.
[34] XU X G, WANG R X, FU C W, et al. SNR-aware low-light image enhancement[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 17693-17703.
[35] WANG R X, ZHANG Q, FU C W, et al. Underexposed photo enhancement using deep illumination estimation[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 6842-6850.
[36] SUN S Q, REN W Q, GAO X W, et al. Restoring images in adverse weather conditions via Histogram transformer[C]∥Computer Vision-ECCV 2024. Cham: Springer, 2025: 111-129.
[37] HAPKE B. Theory of reflectance and emittance spectroscopy[M]. 2nd ed. Cambridge: Cambridge University Press, 2012.
[38] LIU D Y, CHENG W M, QIAN Z, et al. Boundary delineator for Martian crater instances with geographic information and deep learning[J]. Remote Sensing202315(16): 4036.
[39] DETONE D, MALISIEWICZ T, RABINOVICH A. SuperPoint: Self-supervised interest point detection and description[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2018: 224-236.
[40] SARLIN P E, DETONE D, MALISIEWICZ T, et al. SuperGlue: Learning feature matching with graph neural networks[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 4937-4946.
[41] China National Space Administration. Chang’e-2 CCD stereoscopic camera DEM-20 m dataset[EB/OL]. [2025-07-02]. .
[42] LIU J J, REN X, YAN W, et al. A 76 m per pixel global color image dataset and map of Mars by Tianwen-1[J]. Science Bulletin202469(14): 2183-2186.
[43] Lunar Reconnaissance Orbiter Camera. Lunar reconnaissance orbiter camera (LROC) [EB/OL]. [2025-07-02]. .
[44] PASZKE A, GROSS S, MASSA F, et al. PyTorch: An imperative style, high-performance deep learning library[EB/OL]. arXiv preprint1912.01703, 2019.
[45] HUYNH-THU Q, GHANBARI M. Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters200844(13): 800-801.
[46] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing200413(4): 600-612.
[47] ZHANG R, ISOLA P, EFROS A A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 586-595.
文章导航

/