International Journal of Frontiers in Engineering Technology, 2023, 5(2); doi: 10.25236/IJFET.2023.050207.
Mingli Sun, Cheng Hu
College of Engineering, Zhejiang Normal University, Jinhua, China
A monocular visual inertial SLAM algorithm with point-line feature fusion is proposed to solve the problem that the system fails to achieve high accuracy because of the few effective feature points extracted in weak scenes and the tracking failure of the algorithm in rapid movements. With reference to the open-source VINS-Mono system, a modified LSD algorithm is applied to the front end odometer to detect line features so as to extract more feature of the environment while balancing the accuracy and efficiency. We evaluate the performance of our algorithm in public dataset EUROC MAV as well as compare it with VINS-Mono, the experimental results show that the localization accuracy of our algorithm improves about 21.5%.
VIO; Point-line fusion; loop detection; localization
Mingli Sun, Cheng Hu. A monocular visual inertial SLAM algorithm with point-line feature fusion. International Journal of Frontiers in Engineering Technology (2023), Vol. 5, Issue 2: 39-45. https://doi.org/10.25236/IJFET.2023.050207.
[1] Burri, Michael, et al. “The EuRoC micro aerial vehicle datasets.” The International Journal of Robotics Research 35.10 (2016): 1157-1163.
[2] Qin Tong, Peiliang Li, and Shaojie Shen. “Vins-mono: A robust and versatile monocular visual-inertial state estimator.” IEEE Transactionson Robotics 34.4 (2018): 1004-1020.
[3] Wang R, Martin Schwörer, Daniel Cremers. Stereo DSO: Large-scale direct sparse visual odometry with stereo cameras[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy, October 22-29, 2017: 3923-3931.
[4] Jakob Engel, Thomas Schöps, Daniel Cremers. LSD-SLAM: Large-scale direct monocular SLAM [C]//European Conference on Computer Vision. Zurich, Switzerland, September 6-12, 2014: 834-849.
[5] Raúl Mur-Artal, Juan D. Tardós. ORB-SLAM2: An open-source SLAM system for monocular, stereo and RGB-D cameras [J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
[6] Smith P, Reid I D, Davison A J. Real-time monocular SLAM with straight lines [C]// Proceedings of the British Machine Vision Conference 2006. London: British Machine Vision Conference, 2006, 6: 17-26.
[7] Joan Sola, Vidal-Calleja T, Michel Devy. Undelayed initialization of line segments in monocular SLAM [C]. //2009 IEEE/RSJ International Conference on Intelligent Robotics and Systems (IROS 2009). [v.3]: IEEE, 2009: 1553-1558.
[8] Gomez-Ojeda R, Gonzalez-Jimenez J. Robust stereo visual odometry through a probabilistic combination of points and line segments [C]// IEEE International Conference on Robotics & Automation. IEEE, 2016.
[9] Forster C, Pizzoli M, D Scaramuzza SVO: Fast semi-direct monocular visual odometry [C] //IEEE International Conference on Robotics & Automation. IEEE, 2014.
[10] Gomez-Ojeda R, Briales J, Gonzalez-Jimenez J. PL-SVO: Semi-direct Monocular Visual Odometry by combining points and line segments [C]// 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016.
[11] Pumarola A, Vakhitov A, Agudo A, et al.PL-SLAM: real-time mo- nocular visual SLAM with points and lines [C]// IEEE Internation- al Conference on Robotics and Automation (ICRA), 2017: 4503-4508.
[12] QIN T, CAO S, PAN J, et al. A general optimization-based framework for global pose estimation with multiple sensors [EB/OL]. [2022-01-12]. https://arxiv.org/pdf/1901.03638.pdf.
[13] Stefan Leutenegge, Simon Lynen, Michael Bosse, et al. Keyframe-based visual-inertial odometry using nonlinear optimization [J]. International Journal of Robotics Research, 2015, 34(3): 314-334.