Hostname: page-component-586b7cd67f-2brh9 Total loading time: 0 Render date: 2024-11-21T19:42:13.282Z Has data issue: false hasContentIssue false
  • English
  • Français

Stable keypoints selection for 2D LiDAR based place recognition with map data reduction

Published online by Cambridge University Press:  25 April 2022

Lounis Douadi Open the ORCID record for Lounis Douadi [Opens in a new window] ,
Yohan Dupuis  and
Pascal Vasseur Open the ORCID record for Pascal Vasseur [Opens in a new window]
Lounis Douadi*
Affiliation:
Université de Rouen Normandie, LITIS (laboratoire d’informatique, du traitement de l’information et des systèmes), Saint-Étienne-du-Rouvray76800, France
Yohan Dupuis
Affiliation:
CESI (centre des études supérieures industrielles), LINEACT (laboratoire d’innovation numérique pour les entreprises et les apprentissages au service de la compétitivité des territoires), Paris La Défense92074, France
Pascal Vasseur
Affiliation:
Université de Picardie Jules Verne, Laboratoire MIS (modélisation, information, systèmes), Amiens80080, France
*
*Corresponding author. E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper presents a new feature based approach for place recognition using 2D LiDAR (Light Detection And Ranging) data. The main contribution lies in the mapping process. It includes a keypoint selection strategy to model places with persistent keypoints from concatenated LiDAR scans. Our objective is to achieve map data reduction while maintaining good place recognition performace. LiDAR scans are concatenated with a registration algorithm and keypoints are extracted from each scan. Based on a regular grid, our approach measures the occurrence of similar keypoints in each region of interest defined by a grid cell. Only keypoints with occurrences beyond a threshold, qualified as stable keypoints, are kept in the place model called submap. The environment is therefore modeled as a collection of submaps, which constitutes the global map. Place recognition consists in submap matching followed by a two steps geometric verification. In the first stage, optimal parameters are set using corrected data. Mapping parameters satisfy six criteria among which is the spatial distribution distance, which represents another contribution of our work. It gives a measure on how well keypoints are distributed in space. Place recognition optimal parameters are set through global localization. In the second stage, the approach is evaluated using raw data in the contexts of global localization, and loop closure detection in a SLAM framework. The results obtained using popular real data sets show that our approach achieves significant map data reduction (up to $92\%$ ) while maintaining good place recognition performance, comparable to state-of-the-art methods.

Keywords

place recognition2D LiDARkeypoint selectionmap data reductionglobal localizationloop closureSLAM
Type
Research Article
Information
Robotica , Volume 40 , Issue 11 , November 2022 , pp. 3786 - 3810
Copyright
© The Author(s), 2022. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Fernández-Moral, E., Mayol-Cuevas, W. W., Arévalo, V. and González, J., “Fast Place Recognition with Plane-Based Maps,” In: Proceedings of International Conference on Robotics and Automation, Karlsruhe, Germany (2013) pp. 2719–2724.Google Scholar
Sivic, S. and Zisserman, A., “Video Google: Efficient Visual Search of Videos,” In: Toward Category-Level Object Recognition , vol. 4170, (2006) pp. 127–144.Google Scholar
Nistér, D., Stewénius, H., “Scalable Recognition with a Vocabulary Tree,” In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA , vol. 2, (2006) pp. 2161–2168.Google Scholar
Cummins, M. and Newman, P., “FAB-MAP: Probabilistic localization and mapping in the space of appearance,” Int. J. Robot. Res. 27, 647–665 (2008).10.1177/0278364908090961CrossRefGoogle Scholar
Cummins, M. and Newman, P., “Appearance-only SLAM at large scale with FAB-MAP 2. 0,” Int. J. Robot. Res. 30, 1100–1123 (2011).10.1177/0278364910385483CrossRefGoogle Scholar
Bay, H., Tuytelaars, T. and Van Gool, L., “SURF: Speeded Up Robust Features,” In: ECCV 2006 (2006), Graz, Austria, pp. 404–417.Google Scholar
Angeli, A., Filliat, D., Doncieux, S. and Meyer, J. A., “A fast and incremental method for loop-closure detection using bags of visual words,” IEEE Transactions on Robotics , 24, 1027–1037 (2008).Google Scholar
Stumm, E., Mei, C., Lacroix, S., Nieto, J., Hutter, M. and Siegwart, R., “Robust Visual Place Recognition with Graph Kernels,” In: CVPR , Las Vegas, USA (2016) pp. 4535–4544.Google Scholar
Milford, M. and Wyeth, G., “RSeqSLAM: Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights,” In: Proceedings of IEEE ICRA (2012), St-Paul, USA, pp. 1643–1649.Google Scholar
Siam, S. and Zhang, H., “Fast-SeqSLAM: A Fast Appearance Based Place Recognition Algorithm,” In: Proceedings of IEEE ICRA (2017), Singapore, pp. 5702–5708.Google Scholar
Magnusson, M., Andreassonn, H., Nuchter, A. and Lilienthal, A. J., “Appearance-Based Loop Detection from 3D Laser Data Using the Normal Distributions Transform,” In: Proceedings of IEEE ICRA (2009), Kobe, Japan, pp. 23–28.Google Scholar
Magnusson, M., Andreasson, H., Nuchter, A. and Lilienthal, A. J., “Automatic Appearance-Based Loop Detection from 3D Laser Data Using the Normal Distributions Transform,” In: Proceedings of IEEE ICRA (2009), Kobe, Japan, vol. 26, pp. 892–914.Google Scholar
Granström, K. and Schön, T., “Learning to Close the Loop from 3D Point Clouds,” In: Proceedings of IEEE IROS (2010), Taipei, Taiwan, pp. 2089–2209.Google Scholar
Muhammad, N. and Lacroix, S., “Loop Closure Detection Using Small-Sized Signatures from 3D LiDAR Data,” In: Proceedings under IEEE International Workshop on Safety, Security, and Rescue Robotics (2011), Kyoto, Japan.Google Scholar
Rogers, J. G. III and Gregory, J. M., Have I Been Here Before? A Method for Detecting Loop Closure With LiDAR, Tech. Rep. DEC-TR-506, U.S. Army Research Laboratory (2015).10.21236/ADA612636CrossRefGoogle Scholar
Bosse, M. and Zlot, R., “Map Matching and Data Association for Large-Scale Two-Dimensional Laser Scan-Based SLAM,” In: IJRR (International Journal of Robotics Research) , vol. 27 (2008) pp. 667–691.Google Scholar
Zlot, R. and Bosse, M., "Place Recognition Using Keypoint Similarities in 2D Lidar Maps," In: ISER (International Symposium on Experimental Robotics) (2008), Athens, Greece.Google Scholar
Bosse, M. and Zlot, R., “Keypoint design and evaluation for place recognition in 2D lidar maps,” Robot. Auton. Syst. 57(12), 1211–1224 (2009).10.1016/j.robot.2009.07.009CrossRefGoogle Scholar
Granström, K., Callmer, J., Ramos, F. and Nieto, J., “Learning to Detect Loop Closure from Range Data,” In: Proceedings of IEEE of ICRA (2009), Kobe, Japan, pp. 15–22.Google Scholar
Tipaldi, G. D., Spinello, L. and Burgard, W., “Geometrical FLIRT Phrases for Large Scale Place Recognition in 2D Range Data,” In: Proceedings of IEEE of ICRA (2013), Karlsruhe, Germany, pp. 2693–2698.Google Scholar
Tipaldi, G. D. and Arras, K. O., “FLIRT - Interest Regions for 2D Range Data,” In: 2010 IEEE International Conference on Robotics and Automation (2010), Anchorage, USA, pp. 3616–3622.Google Scholar
Tipaldi, G. D., Braun, M. and Arras, K. O., FLIRT: Interest Regions for 2D Range Data with Applications to Robot Navigation, ISER (2010), New Delhi, India.Google Scholar
Himstedt, M. and Maehle, E., “Geometry Matters: Place Recognition in 2D Range Scans Using Geometrical Surface Relations,” In: Proceedings of IEEE ECMR (2009), Mlini/Dubrovnik, Croatia, pp. 1–6.Google Scholar
Himstedt, M., Frost, J., Hellbach, S., Bohme, H. and Maehle, E., “Large Scale Place Recognition in 2D LiDAR Scans Using Geometrical Landmark Relations,” In: Proceedings of IEEE IROS (2014), Chicago, USA, pp. 5030–5035.Google Scholar
Deray, J., Solà, J. and Cetto, J. A., “Word Ordering and Document Adjacency for Large Loop Closure Detection in 2D Laser Maps,” In: IEEE Robotics and Automation Letters (2017).10.1109/LRA.2017.2657796CrossRefGoogle Scholar
rizzini, D. L., Galasso, F. and Caselli, S., “Geometric relation distribution for place recognition,” IEEE Robot. Autom. Lett. 4(2), 523–529 (2019).10.1109/LRA.2019.2891432CrossRefGoogle Scholar
Shan, T., Englot, B., Duarte, F., Ratti, C. and Rus, D., Robust Place Recognition using an Imaging LiDAR. ArXiv, abs/2103.02111.Google Scholar
Fischler, M. A. and Bolles, R. C., “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Commun. ACM 24(6), 381–395 (1981).CrossRefGoogle Scholar
Besl, P. J. and McKay, N. D., “A method for registration of 3-D shapes,” IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 239–256 (1992).10.1109/34.121791CrossRefGoogle Scholar
Naudet-Collette, S., Melbouci, K., Gay-Bellile, V., Ait-Aider, O. and Dhome, M., “Constrained RGBD-SLAM,” Robotica 39(2), 277–290 (2021).10.1017/S0263574720000363CrossRefGoogle Scholar
http://www2.informatik.uni-freiburg.de/%20stachnis/datasets.html.Google Scholar
https://libpointmatcher.readthedocs.io/en/latest/.Google Scholar
https://openslam-org.github.io/flirtlib.html.Google Scholar
https://gtsam.org/.Google Scholar
https://github.com/tipaldi/flirtlib.Google Scholar
https://www.ybliu.com/2020/07/visual-slam-evaluation-aterte.html.Google Scholar