一种基于点和线的视觉惯性SLAM算法
A Point and Line Based Visual Inertial SLAM Algorithm
DOI: 10.12677/CSA.2021.1112291, PDF,   
作者: 张 杰, 裴 东, 高文辉：西北师范大学物理与电子工程学院，甘肃 兰州;甘肃省智能信息技术与应用工程研究中心，甘肃 兰州
关键词: 机器视觉；弱纹理环境；点线特征；数据选择策略；实时性；Machine Vision； Low-Texture Environment； Point and Line Feature； Data Selection Strategy； Real-Time
摘要: 传统的视觉惯性SLAM (Simultaneous Localization and Mapping)算法，在弱纹理场景下，往往存在定位精度差甚至失效的问题，本文提出一种基于点和线特征的视觉惯性SLAM算法。该算法以开源的VINS-Mono (Monocular Visual-Inertial Systems)系统为基础，在此基础上增加了线特征，结合点线特征各自独有的特性，并且提出一种新的数据选择策略，减少了因为线特征的加入而增加的计算量，保证了系统的实时性。实验采用开源数据集Euroc，通过与其他开源算法做对比，对本文算法进行评估，实验结果表明了本文算法的有效性。
Abstract: Traditional visual inertial SLAM (Simultaneous Localization and Mapping) algorithms often have poor localization accuracy or even failure in weak texture scenes. In this paper, a visual inertial SLAM algorithm based on point and line features is proposed. The algorithm is based on the open source VINS-Mono (Monocular Visual-Inertial Systems) system, which adds line features, combines the unique features of point and line features, and proposes a new data selection strategy, which reduces the computational burden caused by line features. The real-time performance of the system is guaranteed. The experiment uses open source data set Euroc and evaluates the algorithm in this paper by comparing it with other open source algorithms. The experimental results show the effectiveness of the algorithm in this paper.
文章引用：张杰, 裴东, 高文辉. 一种基于点和线的视觉惯性SLAM算法[J]. 计算机科学与应用, 2021, 11(12): 2862-2871. https://doi.org/10.12677/CSA.2021.1112291

参考文献

[1] Klein, G. and Murray, D. (2007) Parallel Tracking and Mapping for Small AR Workspaces. 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, Nara, 13-16 November 2007, 225-234. [Google Scholar] [CrossRef] 
[2] Lowe, D.G. (2004) Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60, 91-110. [Google Scholar] [CrossRef] 
[3] Bay, H., Ess, A., Tuytelaars, T., et al. (2008) Speed-ed-Up Robust Features．Computer Vision and Image Understanding, 110, 404-417. [Google Scholar] [CrossRef] 
[4] Rublee, E., Rabaud, V., Konolige, K., et al. (2011) ORB: An Effi-cient Alternative to SIFT or SURF. 2011 International Conference on Computer Vision, Barcelona, 6-13 November 2011, 2564-2571. [Google Scholar] [CrossRef] 
[5] Pumarola, A., Vakhitov, A., Agudo, A., et al. (2017) PL-SLAM: Real-Time Monocular Visual SLAM with Points and Lines. 2017 IEEE International Conference on Robotics and Au-tomation (ICRA), Singapore, 29 May-3 June 2017, 4503-4508. [Google Scholar] [CrossRef] 
[6] Mur-Artal, R., Montiel, J.M.M. and Tardos, J.D. (2015) ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, 31, 1147-1163. [Google Scholar] [CrossRef] 
[7] He, Y., Zhao, J., Guo, Y., et al. (2018) PL-VIO: Tightly-Coupled Monocular Visual-Inertial Odometry Using Point and Line Features. Sensors (Basel), 18, 1159. [Google Scholar] [CrossRef] [PubMed]
[8] Gomez-Ojeda, R., Briales, J. and Gonzalez-Jimenez, J. (2016) PL-SVO: Semi-Direct Monocular Visual Odometry by Combining Points and Line Segments. 2016 IEEE/RSJ International Con-ference on Intelligent Robots and Systems (IROS), Daejeon, 9-14 October 2016, 4211-4216. [Google Scholar] [CrossRef] 
[9] Forster, C., Pizzoli, M. and Scaramuzza, D. (2014) SVO: Fast Semi-Direct Monocular Visual Odometry. IEEE International Conference on Robotics & Automation, Hong Kong, 31 May-7 June, 2014, 15-22. [Google Scholar] [CrossRef] 
[10] 谢晓佳. 基于点线综合特征的双目视觉SLAM方法[D]: [硕士学位论文]. 杭州: 浙江大学, 2017.
[11] Fu, Q., Wang, J., Yu, H., et al. (2020) PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line.
[12] Qin, T., Li, P. and Shen, S. (2018) VINS-Mono: A Robust and Versa-tile Monocular Visual-Inertial State Estimator. IEEE Transactions on Robotics, 34, 1004-1020. [Google Scholar] [CrossRef] 
[13] Von Gioi, R.G., Jakubowicz, J., Morel, J.M., et al. (2010) LSD: A Fast Line Segment Detector with a False Detection Control. IEEE Transactions on Pattern Analysis and Machine In-telligence, 32, 722-732. [Google Scholar] [CrossRef] 
[14] Akinlar, C. and Topal, C. (2011) EDLines: A Real-Time Line Seg-ment Detector with a False Detection Control. Pattern Recognition Letters, 32, 1633-1642. [Google Scholar] [CrossRef] 
[15] Zhang, L. and Koch, R. (2013) An Efficient and Robust Line Segment Matching Approach Based on LBD Descriptor and Pairwise Geometric Consistency. Journal of Visual Com-munication & Image representation, 24, 794-805. [Google Scholar] [CrossRef] 
[16] Chum, O., Matas, J. and Kittler, J. (2003) Locally Optimized RANSAC. In: Pattern Recognition, Lecture Notes in Computer Science, Vol. 2781, Springer, Berlin, 236-243. [Google Scholar] [CrossRef] 
[17] 林利蒙, 王梅. 改进点线特征的双目视觉SLAM算法[J]. 计算机测量与控制, 2019, 27(9): 156-162.
[18] Lin, L.M. and Wang, M. (2019) An Improved Stereo SLAM System through the Combination of Points and Line Segments. Computer Measurement & Control, 27, 156-162.
[19] 王玉良. 基于RGBD的室内移动机器人定位算法研究[D]: [硕士学位论文]. 马鞍山: 安徽工业大学, 2018.
[20] 方琪, 王晓华, 苏杰. 基于分组策略的点线特征融合同步定位与地图构建算法[J]. 激光与光电子学进展, 2021, 58(14): 9.
[21] Burri, M., Nikolic, J., Gohl, P., et al. (2016) The EuRoC Micro Aerial Vehicle Datasets. The International Journal of Robotics Research, 35, 1157-1163. [Google Scholar] [CrossRef]