基于线流特征的视觉惯性SLAM算法
Visual Inertia SLAM Algorithm Based on Point Line Flow Features
摘要: 本文研究了一种基于点和线特征的高效视觉惯性同时定位与建图(SLAM)方法。通过短线融合、线特征均匀分布和自适应阈值提取来改进传统的线检测模型，以获得用于构建SLAM约束的高质量线特征。基于灰度不变性假设和共线性约束，提出了一种线光流跟踪方法。实验结果表明，算法提高了线特征检测与匹配的效率和定位精度。
Abstract: This paper investigates an efficient visual inertial simultaneous localization and mapping (SLAM) method based on point and line features. Improve traditional line detection models by short-term fusion, uniform distribution of line features, and adaptive threshold extraction to obtain high-quality line features for constructing SLAM constraints. A line optical flow tracking method is proposed based on the assumption of grayscale invariance and collinearity constraints. The experimental results show that the algorithm improves the efficiency and positioning accuracy of line feature detection and matching.
文章引用：纪周. 基于线流特征的视觉惯性SLAM算法[J]. 图像与信号处理, 2025, 14(2): 224-231. https://doi.org/10.12677/jisp.2025.142021

参考文献

[1] Huang, G. (2019) Visual-Inertial Navigation: A Concise Review. 2019 International Conference on Robotics and Automation (ICRA), Montreal, 20-24 May 2019, 9572-9582. [Google Scholar] [CrossRef] 
[2] Mourikis, A.I. and Roumeliotis, S.I. (2007) A Multi-State Constraint Kalman Filter for Vision-Aided Inertial Navigation. Proceedings 2007 IEEE International Conference on Robotics and Automation, Rome, 10-14 April 2007, 3565-3572. [Google Scholar] [CrossRef] 
[3] Qin, T., Li, P. and Shen, S. (2018) VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator. IEEE Transactions on Robotics, 34, 1004-1020. [Google Scholar] [CrossRef] 
[4] Gomez-Ojeda, R., Moreno, F., Zuniga-Noel, D., Scaramuzza, D. and Gonzalez-Jimenez, J. (2019) PL-SLAM: A Stereo SLAM System through the Combination of Points and Line Segments. IEEE Transactions on Robotics, 35, 734-746. [Google Scholar] [CrossRef] 
[5] Zhang, G. and Suh, I.H. (2011) Building a Partial 3D Line-Based Map Using a Monocular SLAM. 2011 IEEE International Conference on Robotics and Automation, Shanghai, 9-13 May 2011, 1497-1502. [Google Scholar] [CrossRef] 
[6] Smith, P., Reid, I. and Davison, A. (2006) Real-Time Monocular SLAM with Straight Lines. The British Machine Vision Conference BMVC, Edinburgh, 4-7 September 2006, 17-26.
[7] Zhou, H., Zou, D., Pei, L., Ying, R., Liu, P. and Yu, W. (2015) StructSLAM: Visual SLAM with Building Structure Lines. IEEE Transactions on Vehicular Technology, 64, 1364-1375. [Google Scholar] [CrossRef] 
[8] Ruifang, D., Fremont, V., Lacroix, S., Fantoni, I. and Changan, L. (2017) Line-Based Monocular Graph SLAM. 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), Daegu, 16-18 November 2017, 494-500. [Google Scholar] [CrossRef] 
[9] Fu, Q., Wang, J., Yu, H., Ali, I., Guo, F. and Zhang, H. (2020) PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line.
https://arxiv.org/abs/2009.07462
[10] Zhao, Y. and Vela, P.A. (2018) Good Line Cutting: Towards Accurate Pose Tracking of Line-Assisted VO/VSLAM. 15th European Conference on Computer Vision, Munich, 8-14 September 2018, 527-543. [Google Scholar] [CrossRef] 
[11] Wang, Q., Yan, Z., Wang, J., Xue, F., Ma, W. and Zha, H. (2021) Line Flow Based Simultaneous Localization and Mapping. IEEE Transactions on Robotics, 37, 1416-1432. [Google Scholar] [CrossRef] 
[12] He, Y., Zhao, J., Guo, Y., He, W. and Yuan, K. (2018) PL-VIO: Tightly-Coupled Monocular Visual-Inertial Odometry Using Point and Line Features. Sensors, 18, Article No. 1159. [Google Scholar] [CrossRef] [PubMed]
[13] Akinlar, C. and Topal, C. (2011) Edlines: A Real-Time Line Segment Detector with a False Detection Control. Pattern Recognition Letters, 32, 1633-1642. [Google Scholar] [CrossRef]