Abstract
Changes in appearance present a tremendous problem for the visual localization of an autonomous vehicle in outdoor environments. Data association between the current image and the landmarks in the map can be challenging in cases where the map was built with different environmental conditions. This paper introduces a solution to build and use multi-session maps incorporating sequences recorded in different conditions (day, night, fog, snow, rain, change of season, etc.). During visual localization, we exploit a ranking function to extract the most relevant keyframes from the map. This ranking function is designed to take into account the pose of the vehicle as well as the current environmental condition. In the mapping phase, covering all conditions by constantly adding data to the map leads to a continuous growth in the map size which in turn deteriorates the localization speed and performance. Our map management strategy is an incremental approach that aims to limit the size of the map while keeping it as diverse as possible. Our experiments were performed on real data collected with our autonomous shuttle as well as on a widely used public dataset. The results demonstrate that our keyframe-based ranking function is suitable for long-term scenarios. Our map management algorithm aims to build a map with as much diversity as possible whereas some state of the art approaches tend to filter out the less observed landmarks. This strategy shows a reduction of localization failures while maintaining real-time performance.
Similar content being viewed by others
Notes
To download our dataset please visit http://iplt.ip.uca.fr/datasets/ and enter the following username/password for a read-only access to our ftp server: ipltuser/iplt_ro
References
Arandjelovic R, Gronat P, Torii A, Pajdla T, Sivic J (2016) Netvlad: Cnn architecture for weakly supervised place recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 5297–5307
Bay H, Tuytelaars T, Van Gool L (2006) Surf: Speeded up robust features. In: European conference on computer vision. pp. 404–417. Springer
Berrio JS, Ward J, Worrall S, Nebot E (2019) Identifying robust landmarks in feature-based maps. In: 2019 IEEE Intelligent vehicles symposium (IV). pp. 1166–1172. IEEE
Bouaziz Y, Royer E, Bresson G, Dhome M (2021) Keyframes retrieval for robust long-term visual localization in changing conditions. In: 2021 IEEE 19Th world symposium on applied machine intelligence and informatics (SAMI). pp. 093–100. IEEE
Bouaziz Y, Royer E, Bresson G, Dhome M (2021) Over two years of challenging environmental conditions for localization: the iplt dataset. In: 18Th international conference on informatics in control, automation and robotics
Bürki M, Cadena C, Gilitschenski I, Siegwart R, Nieto J (2019) Appearance-based landmark selection for visual localization. Journal of Field Robotics 36(6):1041–1073
Bürki M, Dymczyk M, Gilitschenski I, Cadena C, Siegwart R, Nieto J (2018) Map management for efficient long-term visual localization in outdoor environments. In: 2018 IEEE Intelligent vehicles symposium (IV). pp. 682–688. IEEE
Bürki M, Gilitschenski I, Stumm E, Siegwart R, Nieto J (2016) Appearance-based landmark selection for efficient long-term visual localization. In: 2016 IEEE/RSJ International conference on intelligent robots and systems (IROS). pp. 4137–4143. IEEE
Carlevaris-Bianco N, Ushani AK, Eustice RM (2015) University of Michigan North Campus long-term vision and lidar dataset. Int J Robot Res 35 (9):1023–1035
Chen C, Wang B, Lu CX, Trigoni A, Markham A (2020) A survey on deep learning for localization and mapping: Towards the age of spatial machine intelligence. ArXiv 2006.12567
Churchill W, Newman P (2012) Practice makes perfect? managing and leveraging visual experiences for lifelong navigation. In: 2012 IEEE International conference on robotics and automation. pp. 4525–4532. IEEE
Churchill W, Newman P (2013) Experience-based navigation for long-term localisation. The International Journal of Robotics Research 32 (14):1645–1661
Clark R, Wang S, Markham A, Trigoni N, Wen H (2017) Vidloc: a deep spatio-temporal model for 6-dof video-clip relocalization. pp 2652–2660 (07. https://doi.org/10.1109/CVPR.2017.284
Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3213–3223
Diaz-Escobar J, Kober V, Gonzalez-Fraga JA (2018) Luift: Luminance invariant feature transform. Math Probl Eng 2018:1–17
Dusmanu M, Rocco I, Pajdla T, Pollefeys M, Sivic J, Torii A, Sattler T (2019) D2-net: a trainable cnn for joint description and detection of local features. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8092–8101
Dymczyk M, Lynen S, Cieslewski T, Bosse M, Siegwart R, Furgale P (2015) The gist of maps-summarizing experience for lifelong localization. In: 2015 IEEE International conference on robotics and automation (ICRA). pp. 2767–2773. IEEE
Dymczyk M, Schneider T, Gilitschenski I, Siegwart R, Stumm E (2016) Erasing bad memories: Agent-side summarization for long-term mapping. In: 2016 IEEE/RSJ International conference on intelligent robots and systems (IROS). pp. 4572–4579. IEEE
Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. The International Journal of Robotics Research 32(11):1231–1237
Gridseth M, Barfoot TD (2020) Deepmel: Compiling visual multi-experience localization into a deep neural network. In: 2020 IEEE International conference on robotics and automation (ICRA). pp. 1674–1681. IEEE
Halodová L, Dvoráková E, Majer F, Vintr T, Mozos OM, Dayoub F, Krajník T (2019) Predictive and adaptive maps for long-term visual navigation in changing environments. In: 2019 IEEE/RSJ International conference on intelligent robots and systems (IROS). pp. 7033–7039. IEEE
Harris CG, Stephens M, et al. (1988) A combined corner and edge detector. In: Alvey vision conference. vol. 15, pp. 10–5244. Citeseer
Jatzkowski I, Wilke D, Maurer M (2018) A deep-learning approach for the detection of overexposure in automotive camera images. In: 2018 21St international conference on intelligent transportation systems (ITSC). pp. 2030–2035. IEEE
Kendall A, Grimes M, Cipolla R (2015) Posenet: a convolutional network for real-time 6-dof camera relocalization. In: Proceedings of the IEEE international conference on computer vision. pp. 2938–2946
Krajník T, Fentanes JP, Hanheide M, Duckett T (2016) Persistent localization and life-long mapping in changing environments using the frequency map enhancement. In: 2016 IEEE/RSJ International conference on intelligent robots and systems (IROS). pp. 4558–4563. IEEE
Krajník T, Vintr T, Molina S, Fentanes JP, Cielniak G, Mozos OM, Broughton G, Duckett T (2019) Warped hypertime representations for long-term autonomy of mobile robots. IEEE Robotics and Automation Letters 4 (4):3310–3317
Laskar Z, Melekhov I, Kalia S, Kannala J (2017) Camera relocalization by computing pairwise relative poses using convolutional neural network. In: Proceedings of the IEEE international conference on computer vision workshops. pp. 929–938
Lébraly P., Royer E, Ait-Aider O, Deymier C, Dhome M (2011) Fast calibration of embedded non-overlapping cameras. In: 2011 IEEE International conference on robotics and automation. pp. 221–227. IEEE
Linegar C, Churchill W, Newman P (2015) Work smart, not hard: Recalling relevant experiences for vast-scale but time-constrained localisation. In: 2015 IEEE International conference on robotics and automation (ICRA). pp. 90–97. IEEE
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2):91–110
MacTavish K, Paton M, Barfoot TD (2018) Selective memory: Recalling relevant experience for long-term visual localization. Journal of Field Robotics 35 (8):1265–1292
Maddern W, Pascoe G, Linegar C, Newman P (2017) 1 year, 1000km: the oxford robotcar dataset. The International Journal of Robotics Research (IJRR) 36(1):3–15. https://doi.org/10.1177/0278364916679498
Maddern W, Pascoe G, Gadd M, Barnes D, Yeomans B, Newman P (2020) Real-time kinematic ground truth for the oxford robotcar dataset. arXiv:2002.10152
Magnago V, Palopoli L, Passerone R, Fontanelli D, Macii D (2019) Effective landmark placement for robot indoor localization with position uncertainty constraints. IEEE Trans Instrum Meas 68(11):4443–4455
Milford MJ, Wyeth GF (2012) Seqslam: Visual route-based navigation for sunny summer days and stormy winter nights. In: 2012 IEEE International conference on robotics and automation. pp. 1643–1649. IEEE
Mühlfellner P, Bürki M, Bosse M, Derendarz W, Philippsen R, Furgale P (2016) Summary maps for lifelong visual localization. Journal of Field Robotics 33(5):561–590
Mur-Artal R, Montiel JMM, Tardos JD (2015) Orb-slam: a versatile and accurate monocular slam system. IEEE Transactions on Robotics 31(5):1147–1163
Murillo AC, Kosecka J (2009) Experiments in place recognition using gist panoramas. In: 2009 IEEE 12Th international conference on computer vision workshops, ICCV workshops. pp. 2196–2203. IEEE
Naseer T, Oliveira GL, Brox T, Burgard W (2017) Semantics-aware visual localization under challenging perceptual conditions. In: 2017 IEEE International conference on robotics and automation (ICRA). pp. 2614–2620. IEEE
Pascoe G, Maddern W, Tanner M, Piniés P, Newman P (2017) Nid-slam: Robust monocular slam using normalised information distance. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1435–1444
Pepperell E, Corke P, Milford M (2016) Routed roads: Probabilistic vision-based place recognition for changing conditions, split streets and varied viewpoints. The International Journal of Robotics Research 35(9):1057–1179
Rosen DM, Mason J, Leonard JJ (2016) Towards lifelong feature-based mapping in semi-static environments. In: 2016 IEEE International conference on robotics and automation (ICRA). pp. 1063–1070. IEEE
Royer E, Marmoiton F, Alizon S, Ramadasan D, Slade M, Nizard A, Dhome M, Thuilot B, Bonjean F (2016) Lessons learned after more than 1000 km in an autonomous shuttle guided by vision. In: 2016 IEEE 19Th international conference on intelligent transportation systems (ITSC). pp. 2248–2253. IEEE
Schneider T, Dymczyk M, Fehr M, Egger K, Lynen S, Gilitschenski I, Siegwart R (2018) Maplab: an open framework for research in visual-inertial mapping and localization. IEEE Robotics and Automation Letters 3(3):1418–1425
Schönberger JL, Pollefeys M, Geiger A, Sattler T (2018) Semantic visual localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 6896–6906
Stenborg E, Sattler T, Hammarstrand L (2020) Using image sequences for long-term visual localization. In: 2020 International conference on 3d vision (3DV). pp. 938–948. https://doi.org/10.1109/3DV50981.2020.00104
Tian Y, Yu X, Fan B, Wu F, Heijnen H, Balntas V (2019) Sosnet: Second order similarity regularization for local descriptor learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 11016–11025
Walch F, Hazirbas C, Leal-Taixe L, Sattler T, Hilsenbeck S, Cremers D (2017) Image-based localization using lstms for structured feature correlation. In: Proceedings of the IEEE international conference on computer vision. pp. 627–637
Yan Z, Sun L, Krajník T, Ruichek Y (2020) Eu long-term dataset with multiple sensors for autonomous driving. In: 2020 IEEE/RSJ International conference on intelligent robots and systems (IROS). pp. 10697–10704. https://doi.org/10.1109/IROS45743.2020.9341406
Yi KM, Trulls E, Lepetit V, Fua P (2016) Lift: Learned invariant feature transform. In: European conference on computer vision. pp. 467–483. Springer
Acknowledgements
This work has been sponsored by the French government research program “Investissements d’Avenir” through the IMobS3 Laboratory of Excellence (ANR-10-LABX-16-01) and the RobotEx Equipment of Excellence (ANR-10-EQPX-44), by the European Union through the Regional Competitiveness and Employment program 2014-2020 (ERDF - AURA region) and by the AURA region.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
We declare that the authors have no conflict of interest on this work.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Bouaziz, Y., Royer, E., Bresson, G. et al. Map management for robust long-term visual localization of an autonomous shuttle in changing conditions. Multimed Tools Appl 81, 22449–22480 (2022). https://doi.org/10.1007/s11042-021-11870-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11870-4