Comparison of Classical and Machine Learning Algorithms for Feature Point Extraction in Rugged Terrain Images for Application in SLAM Algorithms
https://doi.org/10.15514/ISPRAS-2025-37(6)-24
Abstract
The paper proposes a metric for evaluating the performance of feature point extraction algorithms in rough terrain conditions with no clearly defined landmarks or corners. Various feature point detection algorithms are compared for subsequent integration into a SLAM algorithm on board an unmanned aerial vehicle (UAV). The proposed metric, along with other algorithm parameters, is evaluated through experiments conducted in a controlled environment. The advantages of algorithms based on machine learning models are demonstrated.
Keywords
feature point detection algorithms,
SLAM,
SIFT,
LightGlue,
SURF,
ORB,
SuperPoint,
R2D2,
machine learning.
About the Authors
Peter Alexandrovich UKHOV
Moscow Aviation Institute (National Research University)
Russian Federation
Russian Federation
Cand. Sci. (Tech.), Associate professor, Deputy Head of «IT-Centre» MAI since 2020. Research interests: machine learning, computer vision, unmanned aircraft systems software, predictive analytics, aircraft control and navigation systems.
Maria Borisovna BULAKINA
Moscow Aviation Institute (National Research University)
Russian Federation
Russian Federation
Cand. Sci. (Tech.), Associate Professor, Head of the IT Center Department at the Moscow Aviation Institute. Her research interests include software systems development technology, system design, and IT project management.
Sergey Sergeevich KRYLOV
Moscow Aviation Institute (National Research University)
Russian Federation
Russian Federation
Cand. Sci. (Phys.-Math.), Associate Professor, Head of the Department of Computational Mathematics and Programming at the Moscow Aviation Institute. His research interests include software systems development technology and geometric modeling systems.
References
1. Али Б., Садеков Р.Н., Цодокова В.В. Алгоритмы навигации беспилотных летательных аппаратов с использованием систем технического зрения. Гироскопия и навигация. Том 30. №4 (119), 2022, стр.87-105. DOI 10.17285/0869-7035.00105.
2. Smith R.C., Cheeseman P. On the Representation and Estimation of Spatial Uncertainty. The International Journal of Robotics Research. 5 (4): 56–68. 1986. DOI: 10.1177/027836498600500404.
3. Cummins M., Newman P. FAB-MAP: Probabilistic localization and mapping in the space of appearance. The International Journal of Robotics Research. 27 (6): 647–665, 2008. DOI:10.1177/0278364908090961.
4. Yalan Chen, Yimin Zhou, Qin Lv, Kranthi Kumar Deveerasetty A Review of V-SLAM. Conference: 2018 IEEE International Conference on Information and Automation (ICIA). 2018. DOI: 10.1109/ICInfA.2018.8812387.
5. Lowe D.G. Distinctive Image Features from Scale-Invariant Key Points. International Journal of Computer Vision, 2004, 60, 91-110. DOI 10.1023/B:VISI.0000029664.99615.94.
6. Bay H., Tuytelaars T., Van Gool, L. SURF: Speeded Up Robust Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin, Heidelberg. DOI 10.1007/11744023_32.
7. Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary Bradski, Gary Bradski ORB: an efficient alternative to SIFT or SURF. Conference: IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6-13, 2011. DOI: 10.1109/ICCV.2011.6126544.
8. Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich SuperPoint: Self-Supervised Interest Point Detection and Description. Conference: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2018. DOI: 10.1109/CVPRW.2018.00060.
9. Jerome Revaud, Philippe Weinzaepfel, César De Souza, Martin Humenberger. R2D2: Repeatable and Reliable Detector and Descriptor. Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 8-14 December, 2019. DOI 10.48550/arXiv.1906.06195.
10. Marius Muja and David G. Lowe, "Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration", in International Conference on Computer Vision Theory and Applications (VISAPP'09), Vol.1, 2009.
11. Библиотека FLANN [Электронный ресурс] // GitHub. – 2009. – Режим доступа: https://github.com/flann-lib/flann (дата обращения: 04.05.2025).
Review
For citations:
UKHOV P.A., BULAKINA M.B., KRYLOV S.S. Comparison of Classical and Machine Learning Algorithms for Feature Point Extraction in Rugged Terrain Images for Application in SLAM Algorithms. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(6):123-130. (In Russ.) https://doi.org/10.15514/ISPRAS-2025-37(6)-24
Email this article 