{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T04:11:25Z","timestamp":1775103085247,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T00:00:00Z","timestamp":1696032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>Feature extraction plays a crucial role in computer vision and autonomous navigation, offering valuable information for real-time localization and scene understanding. However, although multiple studies investigate keypoint detection and description algorithms in urban and indoor environments, far fewer studies concentrate in unstructured environments. In this study, a multi-task deep learning architecture is developed for keypoint detection and description, focused on poor-featured unstructured and planetary scenes with low or changing illumination. The proposed architecture was trained and evaluated using a training and benchmark dataset with earthy and planetary scenes. Moreover, the trained model was integrated in a visual SLAM (Simultaneous Localization and Maping) system as a feature extraction module, and tested in two feature-poor unstructured areas. Regarding the results, the proposed architecture provides a mAP (mean Average Precision) in a level of 0.95 in terms of keypoint description, outperforming well-known handcrafted algorithms while the proposed SLAM achieved two times lower RMSE error in a poor-featured area with low illumination, compared with ORB-SLAM2. To the best of the authors\u2019 knowledge, this is the first study that investigates the potential of keypoint detection and description through deep learning in unstructured and planetary environments.<\/jats:p>","DOI":"10.3390\/robotics12050137","type":"journal-article","created":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T16:57:06Z","timestamp":1696179426000},"page":"137","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Keypoint Detection and Description through Deep Learning in Unstructured Environments"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4529-6784","authenticated-orcid":false,"given":"Georgios","family":"Petrakis","sequence":"first","affiliation":[{"name":"Spatial Information Systems Unit, School of Mineral Resources Engineering, Technical University of Crete, 73100 Chania, Greece"}]},{"given":"Panagiotis","family":"Partsinevelos","sequence":"additional","affiliation":[{"name":"Spatial Information Systems Unit, School of Mineral Resources Engineering, Technical University of Crete, 73100 Chania, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,30]]},"reference":[{"key":"ref_1","first-page":"8509164","article-title":"A Review of Keypoints\u2019 Detection and Feature Description in Image Registration","volume":"2021","author":"Liu","year":"2021","journal-title":"Hindawi Sci. Program."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/TRO.2016.2624754","article-title":"Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age","volume":"32","author":"Cadena","year":"2016","journal-title":"IEEE Trans. Robot."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/TITS.2022.3175656","article-title":"The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection","volume":"23","author":"Tsintotas","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_4","unstructured":"Harris, C., and Stephens, M. (September, January 31). A Combined Corner and Edge Detector. Proceedings of the Alvey Vision Conference, Manchester, UK."},{"key":"ref_5","unstructured":"Shi, J., and Tomasi, C. (1993). Good Features to Track, Cornell University. Technical Report."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Rosten, E., and Drummond, T. (2006, January 7\u201313). Machine Learning for High-Speed Corner Detection. Proceedings of the ECCV, Graz, Austria.","DOI":"10.1007\/11744023_34"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Alcantarilla, P., Nuevo, J., and Bartoli, A. (2013, January 9\u201313). Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces. Proceedings of the BMVC, Bristol, UK.","DOI":"10.5244\/C.27.13"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6\u201313). ORB: An efficient alternative to SIFT or SURF. Proceedings of the International Conference on Computer Vision, Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive Image Features from Scale-Invariant Keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","article-title":"Speeded-Up Robust Features (SURF)","volume":"110","author":"Bay","year":"2008","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1007\/s12559-018-9591-8","article-title":"Ongoing Evolution of Visual SLAM from Geometry to Deep Learning: Challenges and Opportunities","volume":"10","author":"Li","year":"2018","journal-title":"Cogn. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lategahn, H., Geiger, A., and Kitt, B. (2011, January 9\u201313). Visual SLAM for autonomous ground vehicles. Proceedings of the IEEE ICRA, Shanghai, China.","DOI":"10.1109\/ICRA.2011.5979711"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Singandhupe, A., and La, H. (2019, January 25\u201327). A Review of SLAM Techniques and Security in Autonomous Driving. Proceedings of the IRC, Naples, Italy.","DOI":"10.1109\/IRC.2019.00122"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6907","DOI":"10.1109\/TITS.2021.3063477","article-title":"A Comparative Analysis of LiDAR SLAM-Based Indoor Navigation for Autonomous Vehicles","volume":"23","author":"Zou","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.autcon.2018.10.010","article-title":"Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress","volume":"96","author":"Inzerillo","year":"2018","journal-title":"Autom. Constr."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1049\/iet-rsn.2017.0251","article-title":"State-of-the-art technologies for UAV inspections","volume":"12","author":"Jordan","year":"2018","journal-title":"IET Radar Sonar Navig."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Aulinas, J., Carreras, M., Llado, X., Salvi, J., Garcia, R., Prados, R., and Petillot, Y. (2011, January 6\u20139). Feature extraction for underwater visual SLAM. Proceedings of the OCEANS, Santander, Spain.","DOI":"10.1109\/Oceans-Spain.2011.6003474"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jung, K., Hitchcox, T., and Forbes, J. (2022). Performance Evaluation of 3D Keypoint Detectors and Descriptors on Coloured Point Clouds in Subsea Environments. arXiv.","DOI":"10.1109\/ICRA48891.2023.10160348"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Trabes, E., and Jordan, M.A. (2017). A Node-Based Method for SLAM Navigation in Self-Similar Underwater Environments: A Case Study. Robotics, 6.","DOI":"10.3390\/robotics6040029"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Santos, L.C., Aguiar, A.S., Santos, F.N., Valente, A., and Petry, M. (2020). Occupancy Grid and Topological Maps Extraction from Satellite Images for Path Planning in Agricultural Robots. Robotics, 9.","DOI":"10.3390\/robotics9040077"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Guo, J., Borges, P., Park, C., and Gawel, A. (2018). Local Descriptor for Robust Place Recognition using LiDAR Intensity. arXiv.","DOI":"10.1109\/LRA.2019.2893887"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Oelsch, M., Opdenbosch, V., and Steinbach, E. (2017, January 11\u201313). Survey of Visual Feature Extraction Algorithms in a Mars-like Environment. Proceedings of the ISM, Taichung, Taiwan.","DOI":"10.1109\/ISM.2017.58"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"149","DOI":"10.5194\/isprs-archives-XLII-3-W1-149-2017","article-title":"A Performance comparison of feature detectors for planetary rover mapping and localization","volume":"XLII-3\/W1","author":"Wan","year":"2017","journal-title":"Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1177\/0278364911433135","article-title":"The Devon Island Rover Navigation Dataset","volume":"31","author":"Furgale","year":"2012","journal-title":"Int. J. Robot. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.pss.2018.01.007","article-title":"Illumination invariant feature point matching for high-resolution planetary remote sensing images","volume":"152","author":"Wu","year":"2018","journal-title":"Planet. Space Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/LRA.2017.2777526","article-title":"Where to Look? Predictive Perception with Applications to Planetary Exploration","volume":"3","author":"Otsu","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Giubilato, R., Gentil, C., Vayugundla, M., Schuster, M., Vidal-Calleja, T., and Triebel, R. (2021). GPGM-SLAM: A Robust SLAM System for Unstructured Planetary Environments with Gaussian Process Gradient Maps. arXiv.","DOI":"10.55417\/fr.2022053"},{"key":"ref_28","first-page":"1255","article-title":"ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","volume":"33","author":"Tardos","year":"2016","journal-title":"IEEE Trans. Robot."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Qin, T., Li, P., and Shen, S. (2017). VINS-Mono: A Robust and Versatile MonocularVisual-Inertial State Estimator. arXiv.","DOI":"10.1109\/TRO.2018.2853729"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hong, S., Bangunharcana, A., Park, J.-M., Choi, M., and Shin, H.-S. (2021). Visual SLAM-Based Robotic Mapping Method for Planetary Construction. Sensors, 21.","DOI":"10.3390\/s21227715"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sarlin, P., Cadena, C., Siegwart, R., and Dymczyk, M. (2019, January 15\u201320). From Coarse to Fine: Robust Hierarchical Localization at Large Scale. Proceedings of the CVPR, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., and Rabinovich, A. (2018, January 18\u201322). SuperPoint: Self-Supervised Interest Point Detection and Description. Proceedings of the CVPR, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref_33","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., and Sivic, J. (July, January 26). NetVLAD: CNN Architecture for Weakly Supervised Place Recognition. Proceedings of the CVPR, Las Vegas, NV, USA."},{"key":"ref_34","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the ICCV, Seoul, Republic of Korea."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018, January 18\u201322). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the CVPR, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Elsken, T., Metzen, J., and Hutter, F. (2019). Neural Architecture Search: A Survey. arXiv.","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref_37","unstructured":"Ramachandran, P., Zoph, B., and Le, Q. (2017). Searching for Activation Functions. arXiv."},{"key":"ref_38","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A., Bishop, R., Rueckert, D., and Wang, Z. (July, January 26). Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. Proceedings of the CVPR, Las Vegas, NV, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Li, D., Shi, X., Long, Q., Liu, S., Yang, W., Wang, F., Wei, Q., and Qiao, F. (2020). DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features. arXiv.","DOI":"10.1109\/IROS45743.2020.9340907"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"107193","DOI":"10.1016\/j.patcog.2019.107193","article-title":"UcoSLAM: Simultaneous localization and mapping by fusion of keypoints and squared planar markers","volume":"101","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, L. (2014, January 6\u201312). Microsoft COCO: Common Objects in Context. Proceedings of the ECCV, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_42","unstructured":"Lu, S. (2023). Mars Surface Image (Curiosity Rover) Labeled Data Set Version 1, NASA. Updated January 2023."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s11214-009-9512-y","article-title":"The Lunar Orbiter Laser Altimeter Investigation on the Lunar Reconnaissance Orbiter Mission","volume":"150","author":"Smith","year":"2010","journal-title":"Space Sci. Rev."},{"key":"ref_44","first-page":"2825","article-title":"H-Patches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors","volume":"42","author":"Balntas","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_45","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Calonder, M., Lepetit, V., Strecha, C., and Fua, P. (2010). BRIEF: Binary Robust Independent Elementary Features, Springer. ECCV 2010.","DOI":"10.1007\/978-3-642-15561-1_56"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Schubert, D., Goll, T., Demmel, N., Usenko, V., St\u00fcckler, J., and Cremers, D. (2018, January 1\u20135). The TUM VI Benchmark for Evaluating Visual-Inertial Odometry. Proceedings of the IROS, Madrid, Spain.","DOI":"10.1109\/IROS.2018.8593419"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1109\/LRA.2018.2849609","article-title":"ibow-lcd: An appearance-based loop-closure detection approach using incremental bags of binary words","volume":"3","author":"Ortiz","year":"2018","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/12\/5\/137\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:03:09Z","timestamp":1760130189000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/12\/5\/137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,30]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["robotics12050137"],"URL":"https:\/\/doi.org\/10.3390\/robotics12050137","relation":{},"ISSN":["2218-6581"],"issn-type":[{"value":"2218-6581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,30]]}}}