pith. sign in

arxiv: 2605.17125 · v1 · pith:HUZQ3GFEnew · submitted 2026-05-16 · 💻 cs.CV · cs.LG

Principal Component Analysis for Lunar Crater Detection

Travis Driver , John A. Christian This is my paper

Pith reviewed 2026-05-20 15:15 UTC · model grok-4.3

classification 💻 cs.CV cs.LG
keywords lunar crater detectionprincipal component analysistemplate matchingdigital elevation mapsoptical navigationcrater position estimationsimulated lunar imagery
0
0 comments X

The pith

Principal component analysis of crater elevation maps creates detection templates that outperform hand-picked ones on lunar imagery.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows how applying principal component analysis to digital elevation maps of known lunar craters can automatically build templates for identifying and locating craters in images. This is tested against manually selected templates using simulated lunar scenes, where the data-driven templates yield better detection rates and more precise position estimates. A reader would care if the method holds because crater-based optical navigation is a practical way for spacecraft to determine their location near the Moon without external references. The approach relies on the idea that craters share enough consistent shape features for the main variation patterns to serve as reliable matchers. If the claim is accurate, it points toward less manual work and potentially higher reliability in future lunar missions that use image processing for guidance.

Core claim

The authors present EigenCrater, a method that derives crater templates via principal component analysis on collections of crater digital elevation maps. When these templates are used for matching in simulated lunar imagery, they produce higher detection performance and improved position estimation accuracy relative to templates chosen by hand.

What carries the argument

EigenCrater, the set of principal component templates extracted from crater DEMs that serve as the basis for template matching.

If this is right

  • Automated template creation lowers the effort required to maintain effective crater detectors as new catalog data becomes available.
  • More accurate position estimates from image matching can improve the reliability of optical navigation systems for lunar orbiters and landers.
  • The data-driven selection of principal components may make the templates more robust to small variations in crater appearance than fixed manual choices.
  • The method can be applied to larger sets of craters without a corresponding increase in human selection time.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the templates generalize, they could be tested directly on imagery from ongoing lunar missions to check performance under real lighting and sensor conditions not captured in simulation.
  • The same PCA construction might be tried on elevation data from craters on Mars or other bodies to see whether the homogeneity assumption transfers.
  • Combining the PCA templates with additional image features or classifiers could be explored as a next step to further reduce false detections.

Load-bearing premise

Lunar craters share enough consistent morphological features that the main patterns extracted from their elevation maps form effective and representative detection templates.

What would settle it

Apply the generated templates to a collection of real lunar orbiter images containing independently verified crater positions and measure whether detection rates and position errors remain better than those from hand-picked templates.

read the original abstract

Optical navigation is a critical component for lunar orbiter and lander missions. Image-based crater identification has emerged as a promising technology for optical navigation due to the abundance of craters on the lunar surface and the availability of extensive crater catalogs. Moreover, due to the relative morphological homogeneity among lunar craters, template matching has been identified as a promising approach for identification. In this paper, we propose EigenCrater, an automated crater template generation method based on principal component analysis of crater digital elevation maps (DEMs). We demonstrate superior detection and position estimation performance relative to hand-picked templates on simulated lunar imagery.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes EigenCrater, an automated template generation method that applies principal component analysis to lunar crater digital elevation maps (DEMs) to produce representative templates for image-based crater detection and position estimation. It claims these PCA-derived templates outperform hand-picked templates on simulated lunar imagery for optical navigation applications, leveraging the relative morphological homogeneity of lunar craters.

Significance. If the performance gains hold under rigorous controls, the approach could automate template creation for crater-based optical navigation, reducing reliance on manual selection and potentially improving robustness for lunar orbiter and lander missions. The application of PCA to DEMs for template matching is a reasonable extension of standard computer-vision techniques, but its practical significance hinges on demonstrated generalizability beyond the simulated setting.

major comments (2)
  1. [Abstract] Abstract: the central claim of superior detection and position estimation performance is asserted without any reported quantitative metrics (e.g., detection rates, RMS position error, or statistical significance tests), making it impossible to assess whether the gains are robust or merely due to uncontrolled simulation parameters.
  2. [Abstract] Abstract / Methods (implied): the justification for PCA-based templates rests on the premise of sufficient morphological homogeneity among lunar craters, yet no supporting statistics are provided such as the fraction of variance explained by the first few principal components or ablation results on crater subsets differing in degradation state or rim sharpness.
minor comments (1)
  1. [Abstract] Abstract: the acronym 'EigenCrater' is introduced without a brief definition or reference to how the leading eigenvectors are selected and normalized for template matching.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive review of our manuscript. We address each major comment below, indicating the revisions we will make to strengthen the presentation of our results and methods.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim of superior detection and position estimation performance is asserted without any reported quantitative metrics (e.g., detection rates, RMS position error, or statistical significance tests), making it impossible to assess whether the gains are robust or merely due to uncontrolled simulation parameters.

    Authors: We agree that the abstract would benefit from explicit quantitative support for the performance claims. In the revised manuscript we will augment the abstract with the key metrics from our experiments, including detection rates, RMS position errors, and the results of statistical comparisons between the PCA-derived and hand-picked templates. revision: yes

  2. Referee: [Abstract] Abstract / Methods (implied): the justification for PCA-based templates rests on the premise of sufficient morphological homogeneity among lunar craters, yet no supporting statistics are provided such as the fraction of variance explained by the first few principal components or ablation results on crater subsets differing in degradation state or rim sharpness.

    Authors: The assumption of morphological homogeneity is supported by prior lunar crater studies, yet we concur that direct quantitative evidence would improve the justification. We will add the cumulative variance explained by the leading principal components to the methods section and include an ablation analysis on crater subsets stratified by degradation state and rim sharpness. revision: yes

Circularity Check

0 steps flagged

No significant circularity; standard PCA applied to external data with external benchmarks

full rationale

The paper applies principal component analysis directly to crater DEMs drawn from external catalogs to generate EigenCrater templates, then evaluates detection and position estimation performance against separate hand-picked templates on simulated lunar imagery. No equation or step reduces the claimed superiority to a fitted parameter defined by the result itself, nor does any load-bearing premise collapse into a self-citation or self-definition. The homogeneity premise is stated as background motivation rather than derived from the method, and performance claims rest on comparison to an independent baseline rather than internal consistency alone. This is the normal, non-circular case for an empirical template-generation study.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on the domain assumption of crater morphological homogeneity and on the use of simulated imagery whose fidelity to real lunar conditions is not detailed in the abstract.

axioms (1)
  • domain assumption Lunar craters exhibit relative morphological homogeneity suitable for template matching
    Explicitly stated in the abstract as the basis for identifying template matching as promising.
invented entities (1)
  • EigenCrater no independent evidence
    purpose: Name for the proposed PCA-based automated crater template generation method
    New label introduced for the technique; no independent evidence provided beyond the paper's own description.

pith-pipeline@v0.9.0 · 5615 in / 1167 out tokens · 33856 ms · 2026-05-20T15:15:21.599277+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

50 extracted references · 50 canonical work pages

  1. [1]

    A New Global Database of Lunar Impact Craters>1–2 km: 1. Crater Locations and Sizes, Comparisons With Published Databases, and Global Analysis,

    S. J. Robbins, “A New Global Database of Lunar Impact Craters>1–2 km: 1. Crater Locations and Sizes, Comparisons With Published Databases, and Global Analysis,”J. of Geophysical Research: Planets, V ol. 124, No. 4, 2019, pp. 871–892

    work page 2019

  2. [2]

    An Improved Global Catalog of Lunar Impact Craters (≥1 km) With 3D Morphometric Information and Updates on Global Crater Analysis,

    Y . Wang, B. Wu, H. Xue, X. Li, and J. Ma, “An Improved Global Catalog of Lunar Impact Craters (≥1 km) With 3D Morphometric Information and Updates on Global Crater Analysis,”J. of Geophysical Research: Planets, V ol. 126, No. 9, 2021, p. 10.1029/2020JE006728

    work page doi:10.1029/2020je006728 2021

  3. [3]

    LU5M812TGT: An AI- Powered global database of impact craters≥0.4 km on the Moon,

    R. La Grassa, E. Martellato, G. Cremonese, C. Re, A. Tullo, and S. Bertoli, “LU5M812TGT: An AI- Powered global database of impact craters≥0.4 km on the Moon,”ISPRS J. of Photogrammetry and Remote Sensing, V ol. 220, 2025, pp. 75–84

    work page 2025

  4. [4]

    Crater Detection in Images Using Template Matching,

    A. Thrasher, J. A.Christian, G. Molina, J. Pelgrift, D. Nelson, and C. Adam, “Crater Detection in Images Using Template Matching,”AIAA/AAS Astrodynamics Specialist Conf., Broomfield, Colorado, USA, 2024, pp. 1–18. AAS 24-485

    work page 2024

  5. [5]

    Vision- based navigation and obstacle detection flight results in SLIM lunar landing,

    T. Ishida, S. Fukuda, K. Kariya, H. Kamata, K. Takadama, H. Kojima, S. Sawai, and S. Sakai, “Vision- based navigation and obstacle detection flight results in SLIM lunar landing,”Acta Astronautica, V ol. 226, 2025, pp. 772–781

    work page 2025

  6. [6]

    Eigenfaces for Recognition,

    M. Turk and A. Pentland, “Eigenfaces for Recognition,”J. of Cognitive Neuroscience, V ol. 3, No. 1, 1991, pp. 71–86

    work page 1991

  7. [7]

    J. A. Christian,Fundamentals of Spacecarft Optical Navigation. John Wiley & Sons, 2026

    work page 2026

  8. [8]

    Distinctive image features from scale-invariant keypoints,

    D. G. Lowe, “Distinctive image features from scale-invariant keypoints,”Int. J. of Computer Vision (IJCV), V ol. 60, No. 2, 2004, pp. 91–110

    work page 2004

  9. [9]

    ORB: An efficient alternative to SIFT or SURF,

    E. Rublee, V . Rabaud, K. Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” IEEE Int. Conf. on Computer Vision (ICCV), Barcelona, Spain, 2011, pp. 2564–2571

    work page 2011

  10. [10]

    Visual SLAM for Asteroid Relative Navigation,

    M. Dor, K. A. Skinner, T. Driver, and P. Tsiotras, “Visual SLAM for Asteroid Relative Navigation,” IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) Workshops, Virtual, 2021, pp. 2066–2075

    work page 2021

  11. [11]

    AstroSLAM: Autonomous monocular navigation in the vicinity of a celestial small body—Theory and experiments,

    M. Dor, T. Driver, K. Getzandanner, and P. Tsiotras, “AstroSLAM: Autonomous monocular navigation in the vicinity of a celestial small body—Theory and experiments,”Int. J. of Robotics Research (IJRR), V ol. 43, No. 11, 2024, pp. 1770–1808

    work page 2024

  12. [12]

    Image-based lunar terrain relative navigation without a map: Measurements,

    J. A. Christian, L. Hong, P. McKee, R. Christensen, and T. P. Crain, “Image-based lunar terrain relative navigation without a map: Measurements,”J. of Spacecraft and Rocket (JSR), V ol. 58, No. 1, 2021, pp. 164–181

    work page 2021

  13. [13]

    Generative template-based approach to the automated detection of small craters,

    A. Grumpe and C. W ¨ohler, “Generative template-based approach to the automated detection of small craters,”European Planetary Science Congress, V ol. 8, London, United Kingdom, 2013, pp. 1–2

    work page 2013

  14. [14]

    Deriving morphometric parameters and the simple-to- complex transition diameter from a high-resolution, global database of fresh lunar impact craters (D≥3 km),

    T. Kr ¨uger, S. Hergarten, and T. Kenkmann, “Deriving morphometric parameters and the simple-to- complex transition diameter from a high-resolution, global database of fresh lunar impact craters (D≥3 km),”J. of Geophysical Research: Planets, V ol. 123, No. 10, 2018, pp. 2667–2690

    work page 2018

  15. [15]

    Crater marking and classification using computer vision,

    A. Flores-M ´endez, “Crater marking and classification using computer vision,”Iberoamerican Congress on Pattern Recognition, Coimbra, Portugal, Springer, 2003, pp. 79–86

    work page 2003

  16. [16]

    Optical landmark detection for spacecraft navigation,

    Y . Cheng, A. E. Johnson, L. H. Matthies, and C. F. Olson, “Optical landmark detection for spacecraft navigation,”AAS/AIAA Space Flight Mechanics Meeting, Ponce, Puerto Rico, 2002, pp. 1–19. AAS 02-224

    work page 2002

  17. [17]

    Performance Assessment of Crater- Based Navigation for Autonomous Moon Landing,

    J.-F. Hamel, A. Garant, C. Godin, M. Racicot, and A. Nagaty, “Performance Assessment of Crater- Based Navigation for Autonomous Moon Landing,”AIAA SciTech F orum, Orlando, FL, USA, 2025, pp. 1–14. AIAA 2025-2075

    work page 2025

  18. [18]

    Neural network approach to crater detection for lunar terrain relative navigation,

    L. M. Downes, T. J. Steiner, and J. P. How, “Neural network approach to crater detection for lunar terrain relative navigation,”J. of Aerospace Information Systems (JAIS), V ol. 18, No. 7, 2021, pp. 391–403

    work page 2021

  19. [19]

    Segmentation convolutional neu- ral networks for automatic crater detection on mars,

    D. M. DeLatte, S. T. Crites, N. Guttenberg, E. J. Tasker, and T. Yairi, “Segmentation convolutional neu- ral networks for automatic crater detection on mars,”J. of Selected Topics in Applied Earth Observations and Remote Sensing, V ol. 12, No. 8, 2019, pp. 2944–2957. 18

    work page 2019

  20. [20]

    Mask R-CNN,

    K. He, G. Gkioxari, P. Doll ´ar, and R. Girshick, “Mask R-CNN,”IEEE Int. Conf. on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2961–2969

    work page 2017

  21. [21]

    Implementation of machine learning methods for crater- based navigation,

    S. G. Catalan, B. A. Jones, and J. S. McCabe, “Implementation of machine learning methods for crater- based navigation,”AIAA/AAS Astrodynamics Specialist Conf., Virtual, 2021, pp. 1–18. AAS 21-519

    work page 2021

  22. [22]

    Crater navigation and timing for autonomous lunar orbital operations in small satellites,

    Z. R. McLaughlin, R. E. Gold, S. G. Catalan, B. A. Jones, and R. Zanetti, “Crater navigation and timing for autonomous lunar orbital operations in small satellites,”AAS Guidance, Navigation and Control (GN&C) Conf., Breckenridge, Colorado, USA, 2022, pp. 155–171. AAS-22-025

    work page 2022

  23. [23]

    Developing Robust Crater-Based Terrain Relative Navi- gation Methods Applied to Artemis I Flight Data,

    S. G. Catalan, B. A. Jones, and J. S. McCabe, “Developing Robust Crater-Based Terrain Relative Navi- gation Methods Applied to Artemis I Flight Data,”AIAA/AAS Astrodynamics Specialist Conf., Boston, Massachusetts, USA, 2025. AAS 25-602

    work page 2025

  24. [24]

    You Only Look Once: Unified, real-time object detection,

    J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, real-time object detection,”IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, 2016, pp. 779–788

    work page 2016

  25. [25]

    YOLO-crater model for small crater detection,

    L. Mu, L. Xian, L. Li, G. Liu, M. Chen, and W. Zhang, “YOLO-crater model for small crater detection,” Remote Sensing, V ol. 15, No. 20, 2023, p. 5040

    work page 2023

  26. [26]

    YOLOLens: A deep learning model based on super-resolution to enhance the crater detection of the planetary surfaces,

    R. La Grassa, G. Cremonese, I. Gallo, C. Re, and E. Martellato, “YOLOLens: A deep learning model based on super-resolution to enhance the crater detection of the planetary surfaces,”Remote Sensing, V ol. 15, No. 5, 2023, p. 1171

    work page 2023

  27. [27]

    YOLO-based crater detection for cislunar autonomous optical navigation: Characterization and parametric analysis of angular and area measurement errors,

    T. Kilduff, P. Machuca, and A. Rosengren, “YOLO-based crater detection for cislunar autonomous optical navigation: Characterization and parametric analysis of angular and area measurement errors,” Acta Astronautica, V ol. 240, 2025, pp. 600–620

    work page 2025

  28. [28]

    Ellipse R-CNN: Learning to infer elliptical object from clus- tering and occlusion,

    W. Dong, P. Roy, C. Peng, and V . Isler, “Ellipse R-CNN: Learning to infer elliptical object from clus- tering and occlusion,”IEEE Trans. on Image Processing, V ol. 30, 2021, pp. 2193–2206

    work page 2021

  29. [29]

    Autonomous lunar orbit navigation with Ellipse R-CNN,

    W. Doppenberg, “Autonomous lunar orbit navigation with Ellipse R-CNN,”Masters thesis, 2021

    work page 2021

  30. [30]

    Machine Learning Based Crater Detection for Terrain Relative Navigation,

    C. R. Gnam, T. Chase Jr, and A. J. Liounis, “Machine Learning Based Crater Detection for Terrain Relative Navigation,”AAS Guidance, Navigation and Control (GN&C) Conf., Breckenridge, Colorado, USA, 2025, pp. 1–10

    work page 2025

  31. [31]

    GLD100: The near-global lunar 100 m raster DTM from LROC W AC stereo image data,

    F. Scholten, J. Oberst, K.-D. Matz, T. Roatsch, M. W¨ahlisch, E. Speyerer, and M. Robinson, “GLD100: The near-global lunar 100 m raster DTM from LROC W AC stereo image data,”J. of Geophysical Research: Planets, V ol. 117, No. E12, 2012, pp. 1–12

    work page 2012

  32. [32]

    Lunar Reconnaissance Orbiter wide angle camera photometry: An empirical solution,

    A. Boyd, M. Robinson, and H. Sato, “Lunar Reconnaissance Orbiter wide angle camera photometry: An empirical solution,”Lunar and Planetary Science Conf., No. 1659, 2012, p. 2795

    work page 2012

  33. [33]

    k-means++: The advantages of careful seeding,

    D. Arthur and S. Vassilvitskii, “k-means++: The advantages of careful seeding,”ACM-SIAM Sym. on Discrete Algorithms (SODA), New Orleans, Louisiana, USA, 2007, pp. 1027–1035

    work page 2007

  34. [34]

    Computing vertex normals from polygonal facets,

    G. Th ¨urrner and C. A. W ¨uthrich, “Computing vertex normals from polygonal facets,”J. of Graphics Tools, V ol. 3, No. 1, 1998, pp. 43–46

    work page 1998

  35. [35]

    Photometric functions for photoclinometry and other applications,

    A. S. McEwen, “Photometric functions for photoclinometry and other applications,”Icarus, V ol. 92, No. 2, 1991, pp. 298 – 311

    work page 1991

  36. [36]

    A precise Lunar photometric function,

    A. S. McEwen, “A precise Lunar photometric function,”Lunar and Planetary Science, V ol. 27, Houston, Texas, USA, 1996, pp. 841–842

    work page 1996

  37. [37]

    Characterizing and navigating small bodies with imaging data,

    R. W. Gaskell, O. S. Barnouin-Jha, D. J. Scheeres, A. S. Konopliv, T. Mukai, S. Abe, J. Saito, M. Ishig- uro, T. Kubota, T. Hashimoto, J. Kawaguchi, M. Yoshikawa, K. Shirakawa, T. Kominato, N. Hirata, and H. Demura, “Characterizing and navigating small bodies with imaging data,”Meteoritics & Planetary Science, V ol. 43, No. 6, 2008, pp. 1049–1061

    work page 2008

  38. [38]

    M. K. Shepard,Introduction to Planetary Photometry. Cambridge University Press, 2017

    work page 2017

  39. [39]

    Embree: a kernel framework for efficient CPU ray tracing,

    I. Wald, S. Woop, C. Benthin, G. S. Johnson, and M. Ernst, “Embree: a kernel framework for efficient CPU ray tracing,”ACM Trans. on Graphics (TOG), V ol. 33, No. 4, 2014, pp. 1–8

    work page 2014

  40. [40]

    Trimesh,

    M. Dawson-Haggerty, “Trimesh,”https://github.com/mikedh/trimesh, 2019

    work page 2019

  41. [41]

    Image registration with Fourier-based image correlation: A comprehensive review of developments and applications,

    X. Tong, Z. Ye, Y . Xu, S. Gao, H. Xie, Q. Du, S. Liu, X. Xu, S. Liu, K. Luan,et al., “Image registration with Fourier-based image correlation: A comprehensive review of developments and applications,” IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, V ol. 12, No. 10, 2019, pp. 4062–4081

    work page 2019

  42. [42]

    The Application of Optical Based Feature Tracking to OSIRIS-REx Asteroid Sample Collection,

    R. Olds, A. May, C. Mario, R. Hamilton, C. Debrunner, and A. K, “The Application of Optical Based Feature Tracking to OSIRIS-REx Asteroid Sample Collection,”AAS Guidance, Navigation and Control (GN&C) Conf., Breckenridge, Colorado, USA, 2015, pp. 1–12. AAS 15-124

    work page 2015

  43. [43]

    Lunar crater identification in digital images,

    J. A. Christian, H. Derksen, and R. Watkins, “Lunar crater identification in digital images,”J. of the Astronautical Sciences (JAS), V ol. 68, No. 4, 2021, pp. 1056–1144. 19

    work page 2021

  44. [44]

    Neural Network-Aided Optical Navigation for Precise Lunar Descent Operations,

    S. Andolfo, A. Genova, F. V . Buonomo, A. M. Gargiulo, M. El Awag, P. Federici, R. Teodori, R. La Grassa, C. Re, and G. Cremonese, “Neural Network-Aided Optical Navigation for Precise Lunar Descent Operations,”Aerospace, V ol. 12, No. 3, 2025, p. 195

    work page 2025

  45. [45]

    Lunar Crater Identification using Triangle Reprojection,

    A. C. Thrasher, J. A. Christian, G. Molina, M. Hansen, J. Y . Pelgrift, and D. S. Nelson, “Lunar Crater Identification using Triangle Reprojection,”AIAA/AAS Astrodynamics Specialist Conf., Big Sky, Mon- tana, USA, 2023, pp. 1–15. AAS 23-462

    work page 2023

  46. [46]

    Absolute triangulation algorithms for space exploration,

    S. Henry and J. A. Christian, “Absolute triangulation algorithms for space exploration,”J. of Guidance, Control, and Dynamics, V ol. 46, No. 1, 2023, pp. 21–46

    work page 2023

  47. [47]

    SuperGlue: Learning feature matching with graph neural networks,

    P.-E. Sarlin, D. DeTone, T. Malisiewicz, and A. Rabinovich, “SuperGlue: Learning feature matching with graph neural networks,”IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Virtual, 2020, pp. 4938–4947

    work page 2020

  48. [48]

    Image simulation for space applications with the SurRender soft- ware,

    J. Lebreton, R. Brochard, M. Baudry, G. Jonniaux, A. H. Salah, K. Kanani, M. L. Goff, A. Masson, N. Ollagnier, P. Panicucci,et al., “Image simulation for space applications with the SurRender soft- ware,”ESA Guidance, Navigation & Control Systems (GNC) Conf., Virtual, 2021, pp. 1–16

    work page 2021

  49. [49]

    S., 1979, @doi [Journal of the American Statistical Association] 10.1080/01621459.1979.10481038 , 368, 150

    W. S. Cleveland, “Robust Locally Weighted Regression and Smoothing Scatterplots,”J. of the American Statistical Association, V ol. 74, No. 368, 1979, pp. 829–836, 10.1080/01621459.1979.10481038

    work page doi:10.1080/01621459.1979.10481038 1979

  50. [50]

    Statsmodels: econometric and statistical modeling with Python,

    S. Seabold, J. Perktold,et al., “Statsmodels: econometric and statistical modeling with Python,”SciPy, V ol. 7, No. 1, 2010, pp. 92–96. 20

    work page 2010