Single and Multi Camera Simultaneous Localization and Mapping Using the Extended Kalman Filter
Tóm tắt
Simultaneous Localization and Mapping (SLAM) has received quite a lot of attention in the last decades because of its relevance for many applications centered on a mobile observer, such as service robotics and intelligent transportation systems. This paper focuses on the use of recursive Bayesian filtering, as implemented by the Extendend Kalman Filter (EKF), to face the Visual SLAM problem, i.e., when using data from visual sources. In Monocular SLAM, which uses a single camera as unique source of information, it is not possible to directly estimate the depth of a feature from a single image. To handle the severely non-normal distribution representing such uncertainty, inverse parametrizations were developed, capable to deal with such uncertainty and still relying on Gaussian variables. In the paper, after an introduction to EKF-SLAM, we provide a review of different inverse parametrizations, and we introduce a novel proposal, the Framed Inverse Depth (FID) parametrization, which, in terms of consistency, performs similarly to state of the art Monocular SLAM parametrizations, but at a reduced computational cost. All these parametrizations can be used in a stereo and multi camera setting too. An extensive analysis is presented for both Monocular and stereo SLAM, for a simulated environment widely used in the literature as well as on a widely used real dataset.
Tài liệu tham khảo
Agrawal, M., Konolige, K.: Frameslam: From bundle adjustment to real-time visual mapping. IEEE Trans. Robot. 24(5), 1066–1077 (2008)
Andrade-Cetto, J., Vidal-Calleja, T., Sanfeliu, A.: Unscented transformation of vehicle states in slam. In: Robotics and Automation, 2005. ICRA 2005. In: IEEE International Conference on Proceedings of the 2005, pp. 323–328 (2005). doi:10.1109/ROBOT.2005.1570139
Bailey, T., Nieto, J., Guivant, J., Stevens, M., Nebot, E.: Consistency of the ekf-slam algorithm. In: Proc. of IEEE Intern. Conf. on Intelligent Robots and Systems, pp. 3562–3568 (2006)
Barfoot, T.: Online visual motion estimation using fastslam with sift features. In: 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2005. (IROS 2005), pp. 579–585 (2005). doi:10.1109/IROS.2005.1545444
Castellanos, J.A., Martinez-Cantin, R., Tardos, J.D., Neira, J.: Robocentric map joining: improving the consistency of EKF-SLAM. Robot. Auton. Syst. 55(1), 21–29 (2007)
Ceriani, S., Fontana, G., Giusti, A., Marzorati, D., Matteucci, M., Migliore, D., Rizzi, D., Sorrenti, D.G., Taddei, P.: Rawseeds ground truth collection systems for indoor self-localization and mapping. Auton. Robots 27(4), 353–371 (2009)
Ceriani, S., Marzorati, D., Matteucci, M., Migliore, D., Sorrenti, D.G.: On feature parameterization for ekf-based monocular slam. In: proceedings of 18th World Congress of the International Federation of Automatic Control (IFAC), pp. 6829–6834 (2011)
Chekhlov, D., Pupilli, M., Mayol-Cuevas, W., Calway, A.: Real-time and robust monocular slam using predictive multi-resolution descriptors. In: 2nd International Symposium on Visual Computing. URL http://www.cs.bris.ac.uk/Publications/Papers/2000571.pdf (2006)
Civera, J., Davison, A.J., Montiel, J.M.M.: Inverse depth to depth conversion for monocular slam. In: Proc. of IEEE Intern. Conf. on Robotics and Automation, pp. 2778–2783 (2007)
Civera, J., Grasa, O., Davison., A., Montiel, J.M.M.: 1-point RANSAC for Extended Kalman filtering: Application to real-time structure from motion and visual odometry. JFR 27, 609–631 (2010)
Davison, A.: Real-time simultaneous localisation and mapping with a single camera. In: Proc. of IEEE Intern. Conf. on Computer Vision (2003)
Davison, A.J., Reid, I.D., Molton, N., Stasse, O.: MonoSLAM: real-time single camera SLAM. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)
Durrant-Whyte, H., Bailey, T.: Simultaneous localization and mapping: part i. IEEE Robot. Autom. Mag. 13(2), 99–110 (2006). doi:10.1109/MRA.2006.1638022
Funda, J., Paul, R.: A comparison of transforms and quaternions in robotics. In: Proc. of the 1988 IEEE Intern. Conf. on Robotics and Automation, vol. 2, pp. 886–891 (1988)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004)
Holmes, S., Klein, G., Murray, D.: An o(n 2) square root unscented kalman filter for visual simultaneous localization and mapping. IEEE Trans. Pattern Anal. Mach. Intell. 31(7), 1251–1263 (2009). doi:10.1109/TPAMI.2008.189
Imre, E., Berger, M., Noury, N.: Improved inverse-depth parameterization for monocular simultaneous localization and mapping. In: Proc. of IEEE Intern. Conf. on Robotics and Automation, pp. 381–386 (2009)
Klein, G., Murray, D.: Parallel tracking and mapping on a camera phone. In: Proc. Eigth IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR’09). Orlando (2009)
Lin, K.H., Wang, C.C.: Stereo-based simultaneous localization, mapping and moving object tracking. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Taipei, Taiwan (2010)
Lu, F., Milios, E.: Globally consistent range scan alignment for environment mapping. Auton. Robots 4, 333–349 (1997)
Martinez-Cantin, R., Castellanos, J.: Bounding uncertainty in EKF-SLAM: The robocentric local approach. In: Proc. of IEEE Intern. Conf. on Robotics and Automation (2006)
Marzorati, D., Matteucci, M., Migliore, D., Sorrenti, D.G.: On the use of inverse scaling in monocular slam. In: Proc. of IEEE Intern. Conf. on Robotics and Automation, pp. 2030–2036 (2009)
Migliore, D., Rigamonti, R., Marzorati, D., Matteucci, M., Sorrenti, D.G.: Use a single camera for simultaneous localization and mapping with mobile object tracking in dynamic environments. In: Proceedings of International Workshop on Safe Navigation in Open and Dynamic Environments Application to Autonomous Vehicles (2009)
Montiel, J., Civera, J., Davison, A.J.: Unified inverse depth parametrization for monocular slam. In: Proc. of Robotics: Science and Systems (2006)
Newcombe, R., Davison, A.: Live dense reconstruction with a single moving camera. In: 2010 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1498–1505 (2010)
Pietzsch, T.: Efficient feature parameterisation for visual slam using inverse depth bundles. In: Proc. of BMVC Conf. (2008)
Piniés, P., Paz, L.M., Gálvez-López, D., Tardós, J.D.: CI-Graph simultaneous localization and mapping for three-dimensional reconstruction of large and complex environments using a multicamera system. JFR 27(5), 561–586 (2010)
Pinies, P., Tardos, J.: Large-scale slam building conditionally independent local maps: application to monocular vision. IEEE Trans. Robot. 24(5), 1094–1106 (2008). doi:10.1109/TRO.2008.2004636
Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In: European Conference on Computer Vision, vol. 1, pp. 430–443 (2006). doi:10.1007/11744023_34
Sim, R., Elinas, P., Little, J.: A study of the rao-blackwellised particle filter for efficient and accurate vision-based slam. Int. J. Comput. Vis. 74, 303–318 (2007). doi:10.1007/s11263-006-0021-0
Solà, J.: Consistency of the monocular EKF-SLAM algorithm for three different landmark parametrizations. In: 2010 IEEE Intern. Conf. on Robotics and Automation (ICRA), pp. 3513–3518. IEEE (2010)
Solà, J., Monin, A., Devy, M.: Bicamslam: two times mono is more than stereo. In: 2007 IEEE Intern. Conf. on Robotics and Automation (ICRA), pp. 4795–4800 (2007)
Solà, J., Monin, A., Devy, M., Lemaire, T.: Undelayed initialization in bearing only slam. In: Proc. of Intern. Conf. on Intelligent Robots and Systems, pp. 2499–2504 (2005)
Solà, J., Vidal-Calleja, T., Civera, J., Montiel, J.M.M.: Impact of landmark parametrization on monocular EKF-SLAM with points and lines. Int. J. Comput. Vis. Available online at Springer’s: http://www.springerlink.com/content/5u5176nj521kl3h0/ (2011)
Strasdat, H., Montiel, J., Davison, A.: Real-time monocular slam: why filter? In: Proceedings of IEEE International Conference on and Automation (ICRA), pp. 2657–2664 (2010)
Strasdat, H., Montiel, J.M.M., Davison, A.: Scale drift-aware large scale monocular slam. In: Proceedings of Robotics: Science and Systems. Zaragoza, Spain (2010)
Thrun, S., Montemerlo, M.: The GraphSLAM algorithm with applications to large-scale mapping of urban structures. IJRR 25(5/6), 403–430 (2005)