IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

A New Feature-Based Visual SLAM Using Multi-Channel Dynamic Object Estimation

다중 채널 동적 객체 정보 추정을 통한 특징점 기반 Visual SLAM

  • Received : 2023.10.16
  • Accepted : 2023.12.21
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.

Keywords

Acknowledgement

This work was supported in part by the Materials/Parts Technology Development Program (20023305, Development of intelligent delivery robot with Cloud-Edge AI for last mile delivery between nearby multi-story buildings) funded By the Ministry of Trade, Industry & Energy (MOTIE, Korea), and in part by the "Regional Innovation Strategy (RIS)" through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (MOE) (2023RIS-008).

References

  1. R. Mur-Artal, J. M. M. Montiel, J. D. Tardos, "ORB-SLAM: a Versatile and Accurate Monocular SLAM System," IEEE Trans. Robot., Vol. 31, No. 5, pp. 1147-1163, 2015. https://doi.org/10.1109/TRO.2015.2463671
  2. E Rublee, V Rabaud, K Konolige, G Bradski, "ORB: An Efficient Alternative to SIFT or SURF," In Proc. International Conference on Computer Vision (ICCV), pp. 2564-2571, 2011.
  3. D. Galvez-Lopez, J. D. Tardos, "Bags of Binary Words for Fast Place Recognition in Image Sequences," IEEE Trans. Robot., Vol. 28, No.5, pp. 1188-1197, 2012. https://doi.org/10.1109/TRO.2012.2197158
  4. M. A. Fischler, R. C. Bolles, "Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography," Communications of the ACM, Vol. 24, No. 6, pp. 381-395, 1981. https://doi.org/10.1145/358669.358692
  5. Y. Sheikh, M. Shah, "Bayesian Modeling of Dynamic Scenes for Object Detection," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 27, No. 11, pp. 1778-1792, 2005. https://doi.org/10.1109/TPAMI.2005.213
  6. Y. Sheikh, O. Javed, T. Kanade, "Background Subtraction for Freely Moving Cameras," In Proc. IEEE Int. Conf. Comput. Vis., pp. 1219-1225, 2009.
  7. B. Bescos, J. M. Facil, J. Civera, J. Neira, "DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes," IEEE Robot. Autom. Lett., Vol. 3, No. 4, pp. 4076-4083, 2018. https://doi.org/10.1109/LRA.2018.2860039
  8. D. Lai, C. Li, B. He, "YO-SLAM: A Robust Visual SLAM Towards Dynamic Environments," In Proc. IEEE International Conference on Communications, Information System and Computer Engineering (CISCE), pp. 720-725, 2021.
  9. F. Zhong, S. Wang, Z. Zhang, Y. Wang, "Detect-SLAM: Making Object Detection and SLAM Mutually Beneficial," In Proc. IEEE Winter Conf. Appl. Comput. Vis. (WACV), pp. 1001-1010, 2018.
  10. K. He, G. Gkioxari, P. Dollar, R. Girshick, "Mask R-CNN," In Proc. International Conference on Computer Vision (ICCV), pp. 2961-2969, 2017.
  11. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg, "SSD: Single Shot Multibox Detector," In Proc. Eur. Conf. Comput. Vis., pp. 21-37, 2016.
  12. D. Bolya, C. Zhou, F. Xiao, Y. J. Lee, "Yolact: Real-time Instance Segmentation," In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 9157-9166, 2019.
  13. A. Walcott-Bryant, M. Kaess, H. Johannsson, J. J. Leonard, "Dynamic Pose Graph Slam: Long-term Mapping in Low Dynamic Environments," In Proc. IEEE Int. Conf. Intell. Robots Syst., pp. 1871-1878, 2012.
  14. D. Lee, and M. Hyun, "Solution to the SLAM Problem in Low Dynamic Environments Using a Pose Graph and an RGB-D Sensor," Sensors, Vol. 14, No. 7, pp. 12467-12496, 2014. https://doi.org/10.3390/s140712467
  15. S. Song, H. Lim, S. Jung, H. Myung, "G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-dynamic Environments," IEEE Access, Vol. 10, pp. 21370-21383, 2022. https://doi.org/10.1109/ACCESS.2022.3151133
  16. C. Yu, Z. Liu, X. J. Liu, F. Xie, Y. Yang, Q. Wei, Q. Fei, "DS-SLAM: A Semantic Visual SLAM Towards Dynamic Environments," In Proc. IEEE Int. Conf. Intell. Robots Syst. (IROS), pp. 1168-1174, 2018.
  17. L. Cui, C. Ma, "SOF-SLAM: A Semantic Visual SLAM for Dynamic Environments," IEEE Access, Vol. 7, pp. 166528-166539, 2019. https://doi.org/10.1109/ACCESS.2019.2952161
  18. B. K. P. Horn, B. G. Schunck, "Determining Optical Flow," Artificial Intelligence, Vol. 17, pp. 185-203, 1981. https://doi.org/10.1016/0004-3702(81)90024-2
  19. B. D. Lucas, T. Kanade, "An Iterative Image Registration Technique with an Application to Stereo Vision," In: IJCAI'81: 7th International Joint Conference on Artificial Intelligence, pp. 674-679, 1981.
  20. G. Farneback, "Two-frame Motion Estimation Based on Polynomial Expansion," In Proc. Scandinavian Conference on Image Analysis. Springer, Berlin, Heidelberg, pp. 363-370, 2003.
  21. S. Ren, K. He, R. Girshick, J. Sun., "Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks," In Advances in Neural Information Processing Systems, 2015.
  22. T. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, C. L. Zitnick, "Microsoft coco: Common Objects in Context," In Proc. Eur. Conf. Comput. Vis., pp. 740-755, 2014.
  23. E. Rosten, T. Drummond, "Machine Learning for High-speed Corner Detection," In Proc. Eur. Conf. Comput. Vis., pp. 430-443, 2006.
  24. M. Calonder, V. Lepetit, C. Strecha, P. Fua, "Brief: Binary Robust Independent Elementary Features," In Proc. Eur. Conf. Comput. Vis., pp. 778-792, 2010.
  25. A. Geiger, P. Lenz, R. Urtasun, "Are we Ready for Autonomous Driving? the Kitti Vision Benchmark Suite," In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 3354-3361, 2012.
  26. J. Sturm, N. Engelhard, F. Endres, W. Burgard, D. Cremers, "A Benchmark for the Evaluation of RGB-D SLAM Systems," In Proc. IEEE Int. Conf. Intell. Robots Syst., pp. 573-580, 2012.