Abstract
This paper presents a robust stereo direct visual odometry method with improved robustness against drastic brightness variation and aggressive rotation. It is achieved by incorporating a direct sparse odometry based on image preprocessing, a depth initialization module, and an abend recovery module into the visual odometry framework. The image preprocessing enhances raw camera images, which facilitates more accurate pixels detecting. Meanwhile, a new error function based on image preprocessing is proposed for making direct visual odometry robust to brightness variation in the environment. In the depth initialization module, the Delaunay triangulation algorithm and feature point matching are combined together for efficient and robust depth estimation. Furthermore, in the abend recovery module, we design a lost/abnormal detection method and a robust state restoration strategy to address the tracking lost/abnormal problem in harsh conditions. Evaluation results on KITTI and EuRoC datasets and a light-switch experiment demonstrate that, with the aid of these three modules, the proposed method can achieve state-of-the-art performance, even compared with visual-inertial fusion methods.
Similar content being viewed by others
Notes
When considering the sparsity of the Jacobian matrix \({\varvec{J}}\), \(C_{opt}\simeq O(N^2_{I}N_{p})\).
References
Baker, S., Matthews, I.: Lucas-kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56(3), 221–255 (2004)
Bergmann, P., Wang, R., Cremers, D.: Online photometric calibration of auto exposure video for realtime visual odometry and slam. IEEE Robot. Autom. Lett. 3, 627–634 (2018)
Bloesch, M., Omari, S., Hutter, M., Siegwart, R.: (2015) Robust visual inertial odometry using a direct ekf-based approach. In: Proc. IEEEE/RSJ Int. Conf. Intell. Robot Syst., IEEE, pp 298–304
Burri, M., Nikolic, J., Gohl, P., Schneider, T., Rehder, J., Omari, S., Achtelik, M.W., Siegwart, R.: The euroc micro aerial vehicle datasets. Int. J. Robot. Res. 35, 1157–1163 (2016). https://doi.org/10.1177/0278364915620033
Comport, AI., Malis, E., Rives, P.: (2007) Accurate quadrifocal tracking for robust 3d visual odometry. In: Proc. IEEE Int. Conf. Robot. Autom., pp 40–45, https://doi.org/10.1109/ROBOT.2007.363762
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: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Engel, J., Sturm, J., Cremers, D.: (2013) Semi-dense visual odometry for a monocular camera. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV)
Engel, J., Schöps, T., Cremers, D.: (2014) Lsd-slam: Large-scale direct monocular slam. In: Proc. Eur. Conf. Comput. Vis., Cham, pp 834–849
Engel, J., Stückler, J., Cremers, D.: (2015) Large-scale direct slam with stereo cameras. In: Proc. IEEEE/RSJ Int. Conf. Intell. Robot Syst., pp 1935–1942, https://doi.org/10.1109/IROS.2015.7353631
Engel, J., Usenko, V., Cremers, D.: (2016) A photometrically calibrated benchmark for monocular visual odometry. In: arXiv:1607.02555
Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 611–625 (2018). https://doi.org/10.1109/TPAMI.2017.2658577
Forster, C., Pizzoli, M., Scaramuzza, D.: (2014) Svo: Fast semi-direct monocular visual odometry. In: Proc. IEEE Int. Conf. Robot. Autom., pp 15–22, https://doi.org/10.1109/ICRA.2014.6906584
Fu, Y., Yan, Q., Liao, J., Chow, A.L., Xiao, C.: Real-time dense 3D reconstruction and camera tracking via embedded planes representation. Vis. Comput. 36(10), 2215–2226 (2020)
Geiger, A., Roser, M., Urtasun, R.: Efficient large-scale stereo matching. In: Asian Conference on Computer Vision, pp. 25–38. Springer, Berlin (2010)
Geiger, A., Lenz, P., Urtasun, R.: (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp 3354–3361, https://doi.org/10.1109/CVPR.2012.6248074
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
He, M., Zhu, C., Huang, Q., Ren, B., Liu, J.: A review of monocular visual odometry. Vis. Comput. 36(5), 1053–1065 (2020)
Hirschmuller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. Proc. IEEE Conf. Comput. Vis. Pattern Recogn. 2, 807–814 (2005). https://doi.org/10.1109/CVPR.2005.56
Jin, H., Favaro, P., Soatto, S.: A semi-direct approach to structure from motion. Vis. Comput. 19(6), 377–394 (2003)
Krombach, N., Droeschel, D., Houben, S., Behnke, S.: Feature-based visual odometry prior for real-time semi-dense stereo slam. Robot. Auton. Syst. 109, 38–58 (2018)
Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R., Furgale, P.: Keyframe-based visual-inertial odometry using nonlinear optimization. Int. J. Robot. Res. 34(3), 314–334 (2015). https://doi.org/10.1177/0278364914554813
Liang, H.J., Sanket, N.J., Fermüller, C., Aloimonos, Y.: Salientdso: Bringing attention to direct sparse odometry. IEEE Trans. Autom. Sci. Eng. 16(4), 1619–1626 (2019)
Liu, Y., Chen, X., Gu, T., Zhang, Y., Xing, G.: Real-time camera pose estimation via line tracking. Vis. Comput. 34(6), 899–909 (2018)
Mur-Artal, R., Montiel, J., Tardós, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Robot. 31(5), 1147–1163 (2015)
Newcombe, RA., Lovegrove, SJ., Davison, AJ.: (2011) Dtam: Dense tracking and mapping in real-time. In: Proc. IEEE Int. Conf. Comput. Vis., pp 2320–2327, https://doi.org/10.1109/ICCV.2011.6126513
Ng, P.C., Henikoff, S.: Sift: Predicting amino acid changes that affect protein function. Nucleic Acids Res. 31(13), 3812–3814 (2003)
Pillai, S., Ramalingam, S., Leonard, JJ.: (2016) High-performance and tunable stereo reconstruction. In: Proc. IEEE Int. Conf. Robot. Autom., pp 3188–3195, https://doi.org/10.1109/ICRA.2016.7487488
Pire, T., Fischer, T., Civera, J., De Cristóforis, P., Berlles, JJ.: (2015) Stereo parallel tracking and mapping for robot localization. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp 1373–1378
Qin, T., Li, P., Shen, S.: Vins-mono: a robust and versatile monocular visual-inertial state estimator. IEEE Trans. Robot. 34(4), 1004–1020 (2018)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.R.: ORB: An efficient alternative to sift or surf. Proc. IEEE Int. Conf. Comput. Vis. 11, 2564–2571 (2011)
Shi, J., Tomasi, C.: (2002) Good features to track. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit
Shi, J., Sun, Y., Bai, S., Sun, Z., Tian, Z.: A self-supervised method of single-image depth estimation by feeding forward information using max-pooling layers. Vis. Comput. 37, 815–829 (2020)
Sun, K., Mohta, K., Pfrommer, B., Watterson, M., Liu, S., Mulgaonkar, Y., Taylor, C.J., Kumar, V.: Robust stereo visual inertial odometry for fast autonomous flight. IEEE Robot. Autom. Lett. 3(2), 965–972 (2018)
Wang, R., Schwörer, M., Cremers, D.: (2017) Stereo DSO: Large-scale direct sparse visual odometry with stereo cameras. In: Proc. IEEE Int. Conf. Comput. Vis., Venice, Italy
Wu, X., Pradalier, C.: (2019) Illumination robust monocular direct visual odometry for outdoor environment mapping. In: 2019 International Conference on Robotics and Automation (ICRA), IEEE, pp 2392–2398
Younes, G., Asmar, DC., Zelek, JS.: (2019) FDMO: Feature assisted direct monocular odometry. arXiv preprint arXiv:1804.05422
Zhou, Y., Zhao, J., Luo, C.: A novel method for reconstructing general 3D curves from stereo images. Vis. Comput. 37, 2009–2021 (2020)
Funding
The research was supported by Innovative Research Group Project of the National Natural Science Foundation of China Grant No. 61871265 and National Natural Science Foundation of China Grant No. 61903246.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Supplementary material 1 (mp4 16267 KB)
Rights and permissions
About this article
Cite this article
Miao, R., Liu, P., Wen, F. et al. R-SDSO: Robust stereo direct sparse odometry. Vis Comput 38, 2207–2221 (2022). https://doi.org/10.1007/s00371-021-02278-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02278-0