Abstract
Visual relocalisation is a well-known problem in the robotics community, where chromatic images are used to recognise a place that is being re-visited or re-observed again. Due to the success of deep neural networks in several computer vision tasks, convolutional neural networks have been proposed to address the visual relocalisation problem as well. However, these solutions follow the conventional off-line training in order to generate a model that can be used to regress a camera’s pose w.r.t to an input image. In this work, we present a methodology based on continual learning to address the visual relocalisation problem aiming at performing on-line model training, seeking to generate a model that is updated continuously to learn new acquired images associated with GPS coordinates. Moreover, we apply this methodology to the multi-camera case, where 8 images are acquired from a multi-rig camera, seeking to improve the localisation accuracy, this is, by using a multi-camera, we obtain a set of images observing different viewpoints of the scene for a given GPS position. Therefore, by using a voting scheme, our on-line learned model is capable of performing visual relocalisation with an accuracy of 0.78, performing at 50 fps.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Assa, A., Janabi-Sharifi, F.: Virtual visual servoing for multicamera pose estimation. IEEE/ASME Trans. Mechatron. 20(2), 789–798 (2014)
Blanton, H., Greenwell, C., Workman, S., Jacobs, N.: Extending absolute pose regression to multiple scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 38–39 (2020)
Bresson, G., Yu, L., Joly, C., Moutarde, F.: Urban localization with street views using a convolutional neural network for end-to-end camera pose regression. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 1199–1204. IEEE (2019)
Cabrera-Ponce, A.A., Martinez-Carranza, J.: Aerial geo-localisation for MAVs using PoseNet. In: 2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS), pp. 192–198. IEEE (2019)
Cai, Z., Yu, C., Zhang, J., Ren, J., Zhao, H.: Leveraging localization for multi-camera association. arXiv preprint arXiv:2008.02992 (2020)
Charco, J.L., Sappa, A.D., Vintimilla, B.X., Velesaca, H.O.: Camera pose estimation in multi-view environments: from virtual scenarios to the real world. Image Vis. Comput. 110, 104182 (2021)
Charco, J.L., Vintimilla, B.X., Sappa, A.D.: Deep learning based camera pose estimation in multi-view environment. In: 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 224–228. IEEE (2018)
Clark, R., Wang, S., Markham, A., Trigoni, N., Wen, H.: VidLoc: a deep spatio-temporal model for 6-DoF video-clip relocalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6856–6864 (2017)
Frahm, J.-M., Köser, K., Koch, R.: Pose estimation for multi-camera systems. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 286–293. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28649-3_35
Geppert, M., Liu, P., Cui, Z., Pollefeys, M., Sattler, T.: Efficient 2d-3d matching for multi-camera visual localization. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 5972–5978. IEEE (2019)
Grenzdörffer, T., Günther, M., Hertzberg, J.: YCB-M: a multi-camera RGB-D dataset for object recognition and 6dof pose estimation. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3650–3656. IEEE (2020)
Harmat, A., Trentini, M., Sharf, I.: Multi-camera tracking and mapping for unmanned aerial vehicles in unstructured environments. J. Intell. Robot. Syst. 78(2), 291–317 (2015)
Hee Lee, G., Pollefeys, M., Fraundorfer, F.: Relative pose estimation for a multi-camera system with known vertical direction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 540–547 (2014)
Kasyanov, A., Engelmann, F., Stückler, J., Leibe, B.: Keyframe-based visual-inertial online slam with relocalization. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6662–6669. IEEE (2017)
Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938–2946 (2015)
Le, T., Gjevestad, J.G.O., From, P.J.: Online 3D mapping and localization system for agricultural robots. IFAC-PapersOnLine 52(30), 167–172 (2019)
Lee, G.H., Li, B., Pollefeys, M., Fraundorfer, F.: Minimal solutions for the multi-camera pose estimation problem. Int. J. Robot. Res. 34(7), 837–848 (2015)
Muñoz-Salinas, R., Yeguas-Bolivar, E., Saffiotti, A., Medina-Carnicer, R.: Multi-camera head pose estimation. Mach. Vis. Appl. 23(3), 479–490 (2012)
Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Robot. 31(5), 1147–1163 (2015)
Ott, F., Feigl, T., Loffler, C., Mutschler, C.: ViPR: visual-odometry-aided pose regression for 6DoF camera localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 42–43 (2020)
Pellegrini, L., Graffieti, G., Lomonaco, V., Maltoni, D.: Latent replay for real-time continual learning. arXiv preprint arXiv:1912.01100 (2019)
Remelli, E., Han, S., Honari, S., Fua, P., Wang, R.: Lightweight multi-view 3D pose estimation through camera-disentangled representation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6040–6049 (2020)
Sewtz, M., Luo, X., Landgraf, J., Bodenmüller, T., Triebel, R.: Robust approaches for localization on multi-camera systems in dynamic environments. In: 2021 7th International Conference on Automation, Robotics and Applications (ICARA), pp. 211–215. IEEE (2021)
Valada, A., Radwan, N., Burgard, W.: Deep auxiliary learning for visual localization and odometry. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6939–6946. IEEE (2018)
Xu, Y., Roy, V., Kitani, K.: Estimating 3D camera pose from 2D pedestrian trajectories. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2568–2577. IEEE (2020)
Yang, A.J., Cui, C., Bârsan, I.A., Urtasun, R., Wang, S.: Asynchronous multi-view slam. arXiv preprint arXiv:2101.06562 (2021)
Yang, S., Yi, X., Wang, Z., Wang, Y., Yang, X.: Visual slam using multiple RGB-D cameras. In: 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1389–1395. IEEE (2015)
Yang, Y., Tang, D., Wang, D., Song, W., Wang, J., Fu, M.: Multi-camera visual slam for off-road navigation. Robot. Auton. Syst. 128, 103505 (2020)
Yogamani, S., et al.: WoodScape: a multi-task, multi-camera fisheye dataset for autonomous driving. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9308–9318 (2019)
Zhang, R., Luo, Z., Dhanjal, S., Schmotzer, C., Hasija, S.: PoseNet++: a CNN framework for online pose regression and robot re-localization (2018)
Acknowledgments
The first author is thankful for her scholarship funded by Consejo Nacional de Ciencia y Tecnología (CONACYT) under the grant 727018.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Cabrera-Ponce, A.A., Martin-Ortiz, M., Martinez-Carranza, J. (2021). Continual Learning for Multi-camera Relocalisation. In: Batyrshin, I., Gelbukh, A., Sidorov, G. (eds) Advances in Computational Intelligence. MICAI 2021. Lecture Notes in Computer Science(), vol 13067. Springer, Cham. https://doi.org/10.1007/978-3-030-89817-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-89817-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89816-8
Online ISBN: 978-3-030-89817-5
eBook Packages: Computer ScienceComputer Science (R0)