DI-SLAM: A Real-Time Enhanced RGB-D SLAM for Dynamic Indoor Environments
Source abstract
Abstract
Common visual simultaneous localization and mapping systems are built on the static environment hypothesis and fail to handle the substantial environmental dynamics. Particularly in highly dynamic environments, the pose estimation errors tend to accumulate rapidly, even causing the system to fail. To mitigate this limitation, we have developed DI-SLAM, an enhanced real-time SLAM system for dynamic indoor environments, extending the capabilities of ORB-SLAM3. DI-SLAM introduces a new parallel object detection thread, which employs an enhanced Yolov5s to extract semantic information in every input frame, enabling the filtering of dynamic features for initial tracking and localization. Additionally, we integrate multi-view geometry to further discriminate dynamic feature information, thereby increasing the precision and robustness of localization systems. Finally, experiments were executed on the TUM RGB-D dataset to prove the performance of the proposed algorithm. The results demonstrate strong performance on most datasets, showing a 97.06% improvement in localization accuracy over the original ORB-SLAM3 algorithm in indoor dynamic environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Modular Robots and Swarm Intelligence · Robotic Path Planning Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
Funding
National Natural Science Foundation of China
References (41)
Show source-provided references
1. Engel, J., Schps, T., and Cremers, D. (2014, January 6–12). LSD-SLAM: Large-scale direct monocular SLAM. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10605-2_54 ↗
2. On the representation of spatial uncertainty10.1177/027836498600500404 ↗
3. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM10.1109/TRO.2021.3075644 ↗
4. Yu, C., Liu, Z.X., Liu, X.J., Xie, F.G., Yang, Y., Wei, Q., and Fei, Q. (2018, January 1–5). DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments. Proceedings of the 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8593691 ↗
5. DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes10.1109/LRA.2018.2860039 ↗
6. Optimization RGB-D 3-D Reconstruction Algorithm Based on Dynamic SLAM10.1109/TIM.2023.3248116 ↗
7. Blitz-SLAM: A semantic SLAM in dynamic environments10.1016/j.patcog.2021.108225 ↗
8. DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM10.1109/LRA.2021.3068640 ↗
9. Kochanov, D., Osep, A., Stückler, J., and Leibe, B. (2016, January 9–14). Scene Flow Propagation for Semantic Mapping and Object Discovery in Dynamic Street Scenes. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Republic of Korea.10.1109/IROS.2016.7759285 ↗
10. Zhu, Y., An, H., Wang, H.D., Xu, R.D., Sun, Z.P., and Lu, K. (2024). DOT-SLAM: A Stereo Visual Simultaneous Localization and Mapping (SLAM) System with Dynamic Object Tracking Based on Graph Optimization. Sensors, 24.10.3390/s24144676 ↗
11. Henein, M., Zhang, J., Mahony, R., and Ila, V. (June, January 31). Dynamic SLAM: The Need For Speed. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Paris, France.
12. A review of visual SLAM with dynamic objects10.1108/IR-07-2023-0162 ↗
13. RigidFusion: Robot Localisation and Mapping in Environments With Large Dynamic Rigid Objects10.1109/LRA.2021.3066375 ↗
14. Simultaneous localisation and mapping in dynamic environments (SLAMIDE) with reversible data association
15. Visual SLAM and Structure from Motion in Dynamic Environments: A Survey
16. Visual SLAM and Moving-object Detection for a Small-size Humanoid Robot10.5772/9700 ↗
17. Speeded-Up Robust Features (SURF)10.1016/j.cviu.2007.09.014 ↗
18. DynaTM-SLAM: Fast filtering of dynamic feature points and object-based localization in dynamic indoor environments10.1016/j.robot.2024.104634 ↗
19. DYS-SLAM: A real-time RGBD SLAM combined with optical flow and semantic information in a dynamic environment10.3233/JIFS-234235 ↗
20. Lucas, B.D., and Kanade, T. (1997, January 23–29). An Iterative Image Registration Technique with an Application toStereo Vision. Proceedings of the 7th International Joint Conference on ArtificialIntelligence, Nagoya, Japan.
21. Long, F., Ding, L., and Li, J.F. (2022). DGFlow-SLAM: A Novel Dynamic Environment RGB-D SLAM without Prior Semantic Knowledge Based on Grid Segmentation of Scene Flow. Biomimetics, 7.10.3390/biomimetics7040163 ↗
22. RGB-D SLAM in Dynamic Environments Using Point Correlations10.1109/TPAMI.2020.3010942 ↗
23. Lu, Q., Pan, Y., Hu, L.K., and He, J.S. (2023). A Method for Reconstructing Background from RGB-D SLAM in Indoor Dynamic Environments. Sensors, 23.10.3390/s23073529 ↗
24. Roussillon, C., Gonzalez, A., Solà, J., Codol, J.M., Mansard, N., Lacroix, S., and Devy, M. (2012). RT-SLAM: A Generic and Real-Time Visual SLAM Implementation, Springer.10.1007/978-3-642-23968-7_4 ↗
25. Huang, X.T., Chen, X.B., Zhang, N., He, H.J., and Feng, S. (2024). ADM-SLAM: Accurate and Fast Dynamic Visual SLAM with Adaptive Feature Point Extraction, Deeplabv3pro, and Multi-View Geometry. Sensors, 24.10.3390/s24113578 ↗
26. Yang, H.W., Jiang, P.L., and Wang, F. (2020). Multi-View-Based Pose Estimation and Its Applications on Intelligent Manufacturing. Sensors, 20.10.3390/s20185072 ↗
27. Zhang, Y.C., Li, Y.M., Chen, P.Z., Xie, Y.L., Zheng, S.Q., Hu, Z.Z., and Wang, S.T. (2023). TSG-SLAM: SLAM Employing Tight Coupling of Instance Segmentation and Geometric Constraints in Complex Dynamic Environments. Sensors, 23.10.3390/s23249807 ↗
28. Chen, B.F., and Cai, Z.X. (2008, January 15–17). Mobile robot mapping system and method in dynamic environments. Proceedings of the International Conference on Informational Technology and Environmental System Science, Henan Polytechn Univ, Jiaozuo, China.
29. Chang, Y.M., Hu, J., and Xu, S.Y. (2023). OTE-SLAM: An Object Tracking Enhanced Visual SLAM System for Dynamic Environments. Sensors, 23.10.3390/s23187921 ↗
30. Cong, P.C., Li, J.X., Liu, J.J., Xiao, Y.X., and Zhang, X. (2024). SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information. Sensors, 24.10.3390/s24072102 ↗
31. Kan, X.K., Shi, G.F., Yang, X.R., and Hu, X.W. (2024). YPR-SLAM: A SLAM System Combining Object Detection and Geometric Constraints for Dynamic Scenes. Sensors, 24.10.3390/s24206576 ↗
32. Bai, D.D., Wang, C.Q., Zhang, B., Yi, X.D., and Tang, Y.H. (2016, January 6–10). Matching-Range-Constrained Real-Time Loop Closure Detection with CNNs Features. Proceedings of the IEEE International Conference on Real-Time Computing and Robotics (IEEE RCAR), Angkor Wat, Cambodia.10.1186/s40638-016-0047-x ↗
33. Hu, X., and Lang, J.C. (2021). DOE-SLAM: Dynamic Object Enhanced Visual SLAM. Sensors, 21.10.3390/s21093091 ↗
34. Tian, L.Y., Yan, Y.B., and Li, H.R. (2023). SVD-SLAM: Stereo Visual SLAM Algorithm Based on Dynamic Feature Filtering for Autonomous Driving. Electronics, 12.10.3390/electronics12081883 ↗
35. Yue, S.Z., Wang, Z.J., and Zhang, X.N. (2024). DSOMF: A Dynamic Environment Simultaneous Localization and Mapping Technique Based on Machine Learning. Sensors, 24.10.3390/s24103063 ↗
36. Zhang, J., Henein, M., Mahony, R., and Ila, V. (2020–24, January 24). Robust Ego and Object 6-DoF Motion Estimation and Tracking. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.10.1109/IROS45743.2020.9341552 ↗
37. He, L., Li, S.Y., Qiu, J.T., and Zhang, C.H.M. (2024). DIO-SLAM: A Dynamic RGB-D SLAM Method Combining Instance Segmentation and Optical Flow. Sensors, 24.10.3390/s24185929 ↗
38. Lyu, L., Ding, Y., Yuan, Y.T., Zhang, Y.T., Liu, J.P., and Li, J.X. (2021, January 4–6). DOC-SLAM: Robust Stereo SLAM with Dynamic Object Culling. Proceedings of the 7th International Conference on Automation, Robotics and Applications (ICARA), Prague, Czech Republic.10.1109/ICARA51699.2021.9376418 ↗
39. Li, C., Hu, Y., Liu, J.Q., Jin, J.H., and Sun, J. (2024). ISFM-SLAM: Dynamic visual SLAM with instance segmentation and feature matching. Front. Neurorobot., 18.10.3389/fnbot.2024.1473937 ↗
40. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography10.1145/358669.358692 ↗
41. Sturm, J., Engelhard, N., Endres, F., Burgard, W., and Cremers, D. (2012, January 7–12). A benchmark for the evaluation of RGB-D SLAM systems. Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura-Algarve, Portugal.10.1109/IROS.2012.6385773 ↗