Visual–Inertial Odometry of Structured and Unstructured Lines Based on Vanishing Points in Indoor Environments
Source abstract
Abstract
In conventional point-line visual–inertial odometry systems in indoor environments, consideration of spatial position recovery and line feature classification can improve localization accuracy. In this paper, a monocular visual–inertial odometry based on structured and unstructured line features of vanishing points is proposed. First, the degeneracy phenomenon caused by a special geometric relationship between epipoles and line features is analyzed in the process of triangulation, and a degeneracy detection strategy is designed to determine the location of the epipoles. Then, considering that the vanishing point and the epipole coincide at infinity, the vanishing point feature is introduced to solve the degeneracy and direction vector optimization problem of line features. Finally, threshold constraints are used to categorize straight lines into structural and non-structural features under the Manhattan world assumption, and the vanishing point measurement model is added to the sliding window for joint optimization. Comparative tests on the EuRoC and TUM-VI public datasets validated the effectiveness of the proposed method.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · 3D Surveying and Cultural Heritage · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Tianjin Key Laboratory of Intelligent Control of Electrical Equipment, School of Control Science and Engineering, Tiangong University, Tianjin 300387, China
Institute for Higher Education, Jilin University, Changchun 130012, China
Funding
National Natural Science Foundation of China · Tianjin Natural Science Foundation
References (45)
Show source-provided references
1. Run your visual-inertial odometry on NVIDIA jetson: Benchmark tests on a micro aerial vehicle10.1109/LRA.2021.3075141 ↗
2. ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and Multi-map SLAM10.1109/TRO.2021.3075644 ↗
3. Yang, N., Stumberg, L., Wang, R., and Cremers, D. (2020, January 13–19). D3VO: Deep depth, deep pose and deep uncertainty for monocular visual odometry. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00136 ↗
4. Teng, Z., Han, B., Cao, J., Hao, Q., Tang, X., and Li, Z. (2023). PLI-SLAM: A Tightly-Coupled Stereo Visual-Inertial SLAM System with Point and Line Features. Appl. Sci., 15.10.3390/rs15194678 ↗
5. A vision-based container position measuring system for ARMG10.1177/00202940221110932 ↗
6. Eagle-vision-inspired visual measurement algorithm for UAV’s autonomous landing
7. Visual inertial mapping with non-linear factor recovery10.1109/LRA.2019.2961227 ↗
8. Forster, C., Pizzoli, M., and Scaramuzza, D. (June, January 31). SVO: Fast semi-direct monocular visual odometry. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.
9. Direct sparse odometry10.1109/TPAMI.2017.2658577 ↗
10. Shen, S., Michael, N., and Kumar, V. (2015, January 26–30). Tightly-coupled monocular visual-inertial fusion for autonomous flight of rotorcraft MAVs. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.10.1109/ICRA.2015.7139939 ↗
11. High-precision, consistent EKF-based visual inertial odometry10.1177/0278364913481251 ↗
12. Iterated extended kalman filter based visual-inertial odometry using direct photometric feedback10.1177/0278364917728574 ↗
13. VINS-Mono: A robust and versatile monocular visual-inertial state estimator10.1109/TRO.2018.2853729 ↗
14. Keyframe-based visual-inertial odometry using nonlinear optimization10.1177/0278364914554813 ↗
15. Greene, W., and Roy, N. (August, January 31). Metrically-scaled monocular slam using learned scale factors. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Paris, France.
16. Vidsfm: Robust and accurate structure-from-motion for monocular videos10.1109/TIP.2022.3156375 ↗
17. Lee, S., and Hwang, S. (November, January 27). Elaborate monocular point and line slam with robust initialization. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
18. 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, 18.10.3390/s18041159 ↗
19. Fu, Q., Wang, J., Yu, H., Ali, I., Guo, F., He, Y., and Zhang, H. (2020). PL-VINS: Real-time monocular visual-inertial SLAM with point and line features. arXiv.
20. PLF-VINS: Real-time monocular visual-inertial SLAM with point-line fusion and parallel-line fusion10.1109/LRA.2021.3095518 ↗
21. Gomez-Ojeda, R., Briales, J., and Gonzalez-Jimenez, J. (2016, January 9–14). PL-SVO: Semi-direct monocular visual odometry by combining points and line segments. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Republic of Korea.10.1109/IROS.2016.7759620 ↗
22. UV-SLAM: Unconstrained line-based SLAM using vanishing points for structural mapping10.1109/LRA.2022.3140816 ↗
23. Pumarola, A., Vakhitov, A., Agudo, A., Sanfeliu, A., and Moreno-Noguer, F. (June, January 29). PL-SLAM: Real-time monocular visual SLAM with points and lines. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Singapore.
24. LSD: A fast line segment detector with a false detection control10.1109/TPAMI.2008.300 ↗
25. ORB-SLAM2: An open-source slam system for monocular, stereo, and RGB-D cameras10.1109/TRO.2017.2705103 ↗
26. EDLines: A real-time line segment detector with a false detection control10.1016/j.patrec.2011.06.001 ↗
27. PLC-VIO: Visual-Inertial Odometry Based on Point-Line Constraints10.1109/TASE.2021.3077026 ↗
28. Suárez, I., Buenaposada, J., and Baumela, L. (2022). ELSED: Enhanced line SEgment drawing. arXiv.10.1016/j.patcog.2022.108619 ↗
29. Zhao, Z., Song, T., Xing, B., Lei, Y., and Wang, Z. (2022). PLI-VINS: Visual-Inertial SLAM based on point-line feature fusion in Indoor Environment. Sensors, 22.10.3390/s22145457 ↗
30. Multiple-feature kernel-based probabilistic clustering for unsupervised band selection10.1109/TGRS.2019.2907924 ↗
31. Cipolla, R., Drummond, T., and Robertson, D. (1999, January 13–16). Camera Calibration from Vanishing Points in Image of Architectural Scenes. Proceedings of the British Machine Vision Conference 1999, Nottingham, UK.10.5244/C.13.38 ↗
32. Geometry-based camera calibration using closed-form solution of principal line10.1109/TIP.2020.3048684 ↗
33. Visual SLAM with drift-free rotation estimation in manhattan world10.1109/LRA.2020.3014648 ↗
34. Camposeco, F., and Pollefeys, M. (2015, January 26–30). Using vanishing points to improve visual-inertial odometry. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.10.1109/ICRA.2015.7139926 ↗
35. Li, Y., Yunus, R., Brasch, N., Navab, N., and Tombari, F. (June, January 30). RGB-D SLAM with structural regularities. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China.
36. Vanishing Point Detection and Rail Segmentation Based on Deep Multi-Task Learning10.1109/ACCESS.2020.3019318 ↗
37. Kim, P., Coltin, B., and Kim, H. (2018, January 21–25). Low-drift visual odometry in structured environments by decoupling rotational and translational motion. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia.10.1109/ICRA.2018.8463207 ↗
38. Structure-SLAM: Low-drift monocular SLAM in indoor environments10.1109/LRA.2020.3015456 ↗
39. StructVIO: Visual-inertial odometry with structural regularity of man-made environments10.1109/TRO.2019.2915140 ↗
40. Lu, X., Yao, J., Li, H., Liu, Y., and Zhang, X. (2017, January 24–31). 2-line exhaustive searching for real-time vanishing point estimation in manhattan world. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.10.1109/WACV.2017.45 ↗
41. Peng, X., Liu, Z., Wang, Q., Kim, Y., and Lee, H. (October, January 27). Accurate visual-inertial slam by manhattan frame re-identification. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.
42. Agarwal, S., and Mierle, K. (2018, April 09). Ceres Solver. Available online: http://ceres-solver.org.
43. Structure-from-motion using lines: Representation, triangulation, and bundle adjustment10.1016/j.cviu.2005.06.001 ↗
44. The EuRoC micro aerial vehicle datasets10.1177/0278364915620033 ↗
45. Schubert, D., Goll, T., Demmel, T., Usenko, V., Stückler, J., and Cremers, D. (2018, January 1–5). The TUM VI benchmark for evaluating visual-inertial odometry. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8593419 ↗