Balancing Efficiency and Accuracy: Enhanced Visual Simultaneous Localization and Mapping Incorporating Principal Direction Features
Source abstract
Abstract
In visual Simultaneous Localization and Mapping (SLAM), operational efficiency and localization accuracy are equally crucial evaluation metrics. We propose an enhanced visual SLAM method to ensure stable localization accuracy while improving system efficiency. It can maintain localization accuracy even after reducing the number of feature pyramid levels by 50%. Firstly, we innovatively incorporate the principal direction error, which represents the global geometric features of feature points, into the error function for pose estimation, utilizing Pareto optimal solutions to improve the localization accuracy. Secondly, for loop-closure detection, we construct a feature matrix by integrating the grayscale and gradient direction of an image. This matrix is then dimensionally reduced through aggregation, and a multi-layer detection approach is employed to ensure both efficiency and accuracy. Finally, we optimize the feature extraction levels and integrate our method into the visual system to speed up the extraction process and mitigate the impact of the reduced levels. We comprehensively evaluate the proposed method on local and public datasets. Experiments show that the SLAM method maintained high localization accuracy after reducing the tracking time by 24% compared with ORB SLAM3. Additionally, the proposed loop-closure-detection method demonstrated superior computational efficiency and detection accuracy compared to the existing methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Advanced Image and Video Retrieval Techniques · 3D Surveying and Cultural Heritage
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Space and Environment, Beihang University, Beijing 102206, China
College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Engineering Research Center for Position, Navigation and Time, National University of Defense Technology, Changsha 410073, China
Department of Transportation and Logistics, Dalian University of Technology, Dalian 116024, China
Funding
National Natural Science Foundation of China
References (55)
Show source-provided references
1. Al-Tawil, B., Hempel, T., Abdelrahman, A., and Al-Hamadi, A. (2024). A review of visual SLAM for robotics: Evolution, properties, and future applications. Front. Robot. AI, 11.10.3389/frobt.2024.1347985 ↗
2. LiDAR-based SLAM for robotic mapping: State of the art and new frontiers10.1108/IR-09-2023-0225 ↗
3. Orb-slam3: An accurate open-source library for visual, visual–inertial, and multimap slam10.1109/TRO.2021.3075644 ↗
4. Peng, X., Liu, Z., Li, W., Tan, P., Cho, S.Y., and Wang, Q. (2024, January 13–17). Dvi-slam: A dual visual inertial slam network. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan.10.1109/ICRA57147.2024.10610042 ↗
5. Locus 2.0: Robust and computationally efficient lidar odometry for real-time 3d mapping10.1109/LRA.2022.3181357 ↗
6. Point-LIO: Robust High-Bandwidth Light Detection and Ranging Inertial Odometry10.1002/aisy.202200459 ↗
7. High-precision positioning, perception and safe navigation for automated heavy-duty mining trucks10.1109/TIV.2024.3375273 ↗
8. D2SLAM: Decentralized and Distributed Collaborative Visual-Inertial SLAM System for Aerial Swarm10.1109/TRO.2024.3422003 ↗
9. Ouyang, M., Shi, X., Wang, Y., Tian, Y., Shen, Y., Wang, D., Wang, P., and Cao, Z. (October, January 27). A collaborative visual SLAM framework for service robots. Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.10.1109/IROS51168.2021.9636798 ↗
10. Review of simultaneous localization and mapping (SLAM) for construction robotics applications10.1016/j.autcon.2024.105344 ↗
11. Adaptive chaotification of robot manipulators via neural networks with experimental evaluations10.1016/j.neucom.2015.11.085 ↗
12. Zhu, B., Yu, A., Hou, B., Li, G., and Zhang, Y. (2023). A Novel Visual SLAM Based on Multiple Deep Neural Networks. Appl. Sci., 13.10.3390/app13179630 ↗
13. MonoSLAM: Real-time single camera SLAM10.1109/TPAMI.2007.1049 ↗
14. Klein, G., and Murray, D. (2007, January 13). Parallel tracking and mapping for small AR workspaces. Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, Nara, Japan.10.1109/ISMAR.2007.4538852 ↗
15. Forster, C., Pizzoli, M., and Scaramuzza, D. (2014, January 31). SVO: Fast semi-direct monocular visual odometry. Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.10.1109/ICRA.2014.6906584 ↗
16. Direct sparse mapping10.1109/TRO.2020.2991614 ↗
17. Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6). ORB: An efficient alternative to SIFT or SURF. Proceedings of the 2011 International conference on computer vision (ICCV), Barcelona, Spain.10.1109/ICCV.2011.6126544 ↗
18. ORB-SLAM: A versatile and accurate monocular SLAM system10.1109/TRO.2015.2463671 ↗
19. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
20. Speeded-up robust features (SURF)10.1016/j.cviu.2007.09.014 ↗
21. DeTone, D., Malisiewicz, T., and Rabinovich, A. (2018, January 18–22). Superpoint: Self-supervised interest point detection and description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR), Salt Lake City, UT, USA.10.1109/CVPRW.2018.00060 ↗
22. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras10.1109/TRO.2017.2705103 ↗
23. Qin, T., Cao, S., Pan, J., and Shen, S. (2019). A general optimization-based framework for global pose estimation with multiple sensors. arXiv.
24. Esvio: Event-based stereo visual inertial odometry10.1109/LRA.2023.3269950 ↗
25. Event-based stereo visual odometry10.1109/TRO.2021.3062252 ↗
26. A real-time semantic visual SLAM for dynamic environment based on deep learning and dynamic probabilistic propagation10.1007/s40747-023-01031-5 ↗
27. Wang, Y., Liu, X., Zhao, M., and Xu, X. (2024). VIS-SLAM: A Real-Time Dynamic SLAM Algorithm Based on the Fusion of Visual, Inertial, and Semantic Information. ISPRS Int. J. Geo-Inf., 13.10.3390/ijgi13050163 ↗
28. Alamanos, I., and Tzafestas, C. (2023). ORB-LINE-SLAM: An Open-Source Stereo Visual SLAM System with Point and Line Features. TechRxiv.10.36227/techrxiv.21691949 ↗
29. VPL-SLAM: A Vertical Line Supported Point Line Monocular SLAM System10.1109/TITS.2024.3369168 ↗
30. Szeliski, R. (2022). Computer Vision: Algorithms and Applications, Springer Nature.10.1007/978-3-030-34372-9 ↗
31. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
32. Brown, M., Szeliski, R., and Winder, S. (2005, January 20–26). Multi-image matching using multi-scale oriented patches. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.
33. LOCATOR: Low-power ORB accelerator for autonomous cars10.1016/j.jpdc.2022.12.005 ↗
34. Visual-inertial mapping with non-linear factor recovery10.1109/LRA.2019.2961227 ↗
35. Geneva, P., Eckenhoff, K., Lee, W., Yang, Y., and Huang, G. (2020, January 31). Openvins: A research platform for visual-inertial estimation. Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France.10.1109/ICRA40945.2020.9196524 ↗
36. Li, Y., Wei, W., and Zhu, H. (2023). Incremental Bag of Words with Gradient Orientation Histogram for Appearance-Based Loop Closure Detection. Appl. Sci., 13.10.3390/app13116481 ↗
37. Dalal, N., and Triggs, B. (2005, January 20–26). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.
38. Zhang, J., Ai, D., Xiang, Y., Wang, Y., Chen, X., and Chang, X. (2018, January 17–20). Bag-of-words based loop-closure detection in visual SLAM. Proceedings of the 2018 Advanced Optical Imaging Technologies, Bellingham, DC, USA.10.1117/12.2500819 ↗
39. Wang, H., Wang, C., and Xie, L. (2020, January 25–29). Online visual place recognition via saliency re-identification. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, LA, USA.10.1109/IROS45743.2020.9341703 ↗
40. Fast and effective loop closure detection to improve SLAM performance10.1007/s10846-017-0718-z ↗
41. Loop closure detection based on image covariance matrix matching for visual SLAM10.1007/s12555-020-0730-0 ↗
42. Chen, Z., Lam, O., Jacobson, A., and Milford, M. (2014). Convolutional neural network-based place recognition. arXiv.
43. Unsupervised learning to detect loops using deep neural networks for visual SLAM system10.1007/s10514-015-9516-2 ↗
44. Srvio: Super robust visual inertial odometry for dynamic environments and challenging loop-closure conditions10.1109/TRO.2023.3268591 ↗
45. Hines, A.D., Stratton, P.G., Milford, M., and Fischer, T. (2024, January 13–17). VPRTempo: A fast temporally encoded spiking neural network for visual place recognition. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan.10.1109/ICRA57147.2024.10610918 ↗
46. Cheng, X., Zhang, Y., Kang, M., Wang, J., Jiao, J., Dong, L., and Jiao, L. (2024). A Semantic Spatial Structure-Based Loop Detection Algorithm for Visual Environmental Sensing. Remote Sens., 16.10.3390/rs16101720 ↗
47. Li, J., Wang, P., Ni, C., Zhang, D., and Hao, W. (2022). Loop Closure Detection for Mobile Robot based on Multidimensional Image Feature Fusion. Machines, 11.10.3390/machines11010016 ↗
48. Arshad, S., and Kim, G.W. (2021, January 12–15). Semantics aware loop closure detection in visual SLAM. Proceedings of the 2021 21st International Conference on Control, Automation and Systems (ICCAS), Jeju, Republic of Korea.10.23919/ICCAS52745.2021.9649851 ↗
49. Yuan, Z., Xu, K., Zhou, X., Deng, B., and Ma, Y. (2021). SVG-Loop: Semantic–visual–geometric information-based loop closure detection. Remote Sens., 13.10.3390/rs13173520 ↗
50. Semantic loop closure detection with instance-level inconsistency removal in dynamic industrial scenes10.1109/TII.2020.3010580 ↗
51. Feature selection based on mutual information with correlation coefficient10.1007/s10489-021-02524-x ↗
52. The EuRoC micro aerial vehicle datasets10.1177/0278364915620033 ↗
53. Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16–21). Are we ready for autonomous driving? the kitti vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗
54. Klenk, S., Chui, J., Demmel, N., and Cremers, D. (October, January 27). Tum-vie: The tum stereo visual-inertial event dataset. Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.10.1109/IROS51168.2021.9636728 ↗
55. The UMA-VI dataset: Visual–inertial odometry in low-textured and dynamic illumination environments10.1177/0278364920938439 ↗