Abstract
Multi-perspective camera systems pointing into all directions represent an increasingly interesting solution for visual localization and mapping. They combine the benefits of omni-directional measurements with a sufficient baseline for producing measurements in metric scale. However, the observability of metric scale suffers from degenerate cases if the cameras do not share any overlap in their field of view. This problem is of particular importance in many relevant practical applications, and it impacts most heavily on the difficulty of bootstrapping the structure-from-motion process. The present paper introduces a complete real-time pipeline for visual odometry with non-overlapping, multi-perspective camera systems, and in particular presents a solution to the scale initialization problem. We evaluate our method on both simulated and real data, thus proving robust initialization capacity as well as best-in-class performance regarding the overall motion estimation accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Keyframes are simply frames that are retained in a buffer of frames due to sufficient local distinctiveness [10].
References
Agarwal, S., Mierle, K., et al.: Ceres solver. http://ceres-solver.org
Bradski, G.: The OpenCV library. Dr. Dobb’s J. Softw. Tools (2000)
Clipp, B., Kim, J.H., Frahm, J.M., Pollefeys, M., Hartley, R.: Robust 6DOF motion estimation for non-overlapping, multi-camera systems. In: Proceedings of the IEEE Workshop on Applications of Computer Vision, Washington, DC, USA, pp. 1–8 (2008)
Engel, J., Schöps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834–849. Springer, Cham (2014). doi:10.1007/978-3-319-10605-2_54
Guennebaud, G., Jacob, B., et al.: Eigen v3 (2010). http://eigen.tuxfamily.org
Hartley, R., Trumpf, J., Yuchao, D., Li, H.: Rotation averaging. Int. J. Comput. Vis. (IJCV) 103(3), 267–305 (2013)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, New York (2004)
Horaud, R., Dornaika, F.: Hand-eye calibration. Int. J. Robot. Res. (IJRR) 14(3), 195–210 (1995)
Kazik, T., Kneip, L., Nikolic, J., Pollefeys, M., Siegwart, R.: Real-time 6D stereo visual odometry with non-overlapping fields of view. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, USA (2012)
Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR), Nara, Japan (2007)
Kneip, L., Furgale, P.: OpenGV: a unified and generalized approach to real-time calibrated geometric vision. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Hongkong (2014)
Kneip, L., Furgale, P., Siegwart, R.: Using multi-camera systems in robotics: efficient solutions to the NPnP problem. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany (2013)
Kneip, L., Li, H.: Efficient computation of relative pose for multi-camera systems. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, USA (2014)
Kneip, L., Li, H., Seo, Y.: UPnP: an optimal O(n) solution to the absolute pose problem with universal applicability. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 127–142. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_9
Kneip, L., Lynen, S.: Direct optimization of frame-to-frame rotation. In: Proceedings of the International Conference on Computer Vision (ICCV), Sydney, Australia (2013)
Kneip, L., Scaramuzza, D., Siegwart, R.: A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, USA (2011)
Konolige, K., Agrawal, M., Solà , J.: Large scale visual odometry for rough terrain. In: Proceedings of the International Symposium on Robotics Research (ISRR), Hiroshima, Japan (2007)
Li, H., Hartley, R., Kim, J.H.: A linear approach to motion estimation using generalized camera models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, USA, pp. 1–8 (2008)
Mur-Artal, R., Montiel, J.M.M., Tardós, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Robot. (T-RO) 31(5), 1147–1163 (2015)
Newcombe, R., Lovegrove, S., Davison, A.: DTAM: dense tracking and mapping in real-time. In: Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain (2011)
Newcombe, R.A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A.J., Kohli, P., Shotton, J., Hodges, S., Fitzgibbon, A.: Kinectfusion: real-time dense surface mapping and tracking. In: Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR) (2011)
Nistér, D., Naroditsky, O., Bergen, J.: Visual odometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, pp. 652–659 (2004)
Nistér, D., Stewénius, H.: A minimal solution to the generalized 3-point pose problem. J. Math. Imaging Vis. (JMIV) 27(1), 67–79 (2006)
Pless, R.: Using many cameras as one. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Madison, WI, USA, pp. 587–593 (2003)
Steinbrücker, F., Sturm, J., Cremers, D.: Real-time visual odometry from dense RGB-D images. In: IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (2011)
Stewénius, H., Engels, C., Nistér, D.: Recent developments on direct relative orientation. ISPRS J. Photogramm. Remote Sens. 60(4), 284–294 (2006)
Stewénius, H., Nistér, D.: Solutions to minimal generalized relative pose problems. In: Workshop on Omnidirectional Vision (ICCV), Beijing, China (2005)
Strasdat, H., Davison, A.: Scale drift-aware large scale monocular SLAM. In: Proceedings of Robotics: Science and Systems (RSS), Zaragoza, Spain (2010)
Tykkälä, T., Audras, C., Comport, A.I.: Direct iterative closest point for real-time visual odometry. In: IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (2011)
Whelan, T., Johannsson, H., Kaess, M., Leonard, J.J., McDonald, J.: Robust real-time visual odometry for dense RGB-D mapping. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wang, Y., Kneip, L. (2017). On Scale Initialization in Non-overlapping Multi-perspective Visual Odometry. In: Liu, M., Chen, H., Vincze, M. (eds) Computer Vision Systems. ICVS 2017. Lecture Notes in Computer Science(), vol 10528. Springer, Cham. https://doi.org/10.1007/978-3-319-68345-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-68345-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68344-7
Online ISBN: 978-3-319-68345-4
eBook Packages: Computer ScienceComputer Science (R0)