Education, Science, Technology, Innovation and Life
Open Access
Sign In

A Survey on Mobile Robot Visual Relocalization in Complex Dynamic Scenes

Download as PDF

DOI: 10.23977/acss.2026.100113 | Downloads: 27 | Views: 393

Author(s)

Shichu Sun 1

Affiliation(s)

1 Yunnan Normal University, Kunming, Yunnan, China

Corresponding Author

Shichu Sun

ABSTRACT

Visual relocalization is key to enabling continuous autonomous navigation of mobile robots. This survey systematically reviews research progress on visual relocalization technology in complex dynamic scenes, focusing on the issues of excessive computational load and mismatches caused by dynamic disturbances in real environments. It explores the evolutionary trajectory from global representations and local matching to semantic learning methods, revealing that the core mechanisms for handling dynamic disturbances have shifted from passive feature filtering to "active suppression" using spatial attention, adaptive matching, and soft weighting. Taking into account the deployment requirements of mobile robots, the paper summarizes engineering solutions that encompass lightweight matching and multimodal priors, and envisions future research directions such as deep semantic-geometric collaboration and incremental map evolution. These insights provide theoretical reference and practical guidance for the design of robust localization systems.

KEYWORDS

Visual Relocalization, Mobile Robots, Dynamic Scenes, Robustness

CITE THIS PAPER

Shichu Sun. A Survey on Mobile Robot Visual Relocalization in Complex Dynamic Scenes. Advances in Computer, Signals and Systems (2026). Vol. 10, No. 1, 102-107. DOI: http://dx.doi.org/10.23977/acss.2026.100113.

REFERENCES

[1] Shotton, Jamie, Glocker, Ben, Zach, Christopher, Izadi, Shahram, Criminisi, Antonio, and Fitzgibbon, Andrew. "Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2930–2937, 2013. doi: 10.1109/CVPR.2013.377 
[2] Kendall, A., Grimes, M., and Cipolla, R. "PoseNet: A convolutional network for real-time 6-DOF camera relocalization". Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2912–2920, 2015. doi: 10.1109/ICCV.2015.333 
[3] Kendall, A., Gal, Y., and Cipolla, R. "Modelling Uncertainty in Deep Learning for Camera Relocalization". arXiv preprint arXiv:1509.05909v2, 2016. 
[4] Soares, J. C. V., and others. "Visual Localization and Mapping in Dynamic and Changing Environments". Journal of Intelligent & Robotic Systems, 109:95, 2023. doi: 10.1007/s10846-023-02019-6 
[5] Toft, C., and others. "Long-Term Visual Localization Revisited". IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4):2074–2088, 2020. doi: 10.1109/TPAMI.2020.3032010 
[6] Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., and Sivic, J. "NetVLAD: CNN architecture for weakly supervised place recognition". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5297–5307, 2016. doi: 10.1109/CVPR.2016.572 
[7] Do, T., and Sinha, S. "Improved Scene Landmark Detection for Camera Localization". Proceedings of the International Conference on 3D Vision (3DV), 975–984, 2024. doi: 10.1109/3DV62453.2024.00069 
[8] Huang, K. "Overview of Visual SLAM Technology: From Traditional to Deep Learning Methods". Advances in Computer, Signals and Systems, 7(10):76–81, 2023. doi: 10.23977/acss.2023.071011 
[9] Sarlin, Paul-Edouard, Cadena, Cesar, Siegwart, Roland, and Dymczyk, Martin. "From coarse to fine: Robust hierarchical localization at large scale". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12716–12725, 2019. doi: 10.1109/CVPR.2019.01300 
[10] Germain, H., and others. "Learned place recognition". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. doi: 10.1109/CVPR52729.2023.00890 
[11] Luo, Z., and others. "Scalable visual localization". Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2024. doi: 10.1109/ICRA.2024.101247 
[12] Sarlin, Paul-Edouard, DeTone, Daniel, Malisiewicz, Tomasz, and Rabinovich, Andrew. "SuperGlue: Learning feature matching with graph neural networks". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4938–4947, 2020. doi: 10.1109/CVPR42600.2020.00499
[13] Zhao, X., and others. "Robust feature matching". Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023. doi: 10.1109/ICCV.2023.00714 
[14] Lindenberger, P., Sarlin, P.-E., and Pollefeys, M. "LightGlue: Local Feature Matching at Light Speed". Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023. doi: 10.1109/ICCV51070.2023.01633 
[15] Chen, Y., and others. "Geometry-aware localization". IEEE Transactions on Robotics, 2024. doi: 10.1109/ TRO.2024.3351982 
[16] Brachmann, Eric, Krull, Alexander, Nowozin, Sebastian, and others. "DSAC – Differentiable RANSAC for Camera Localization". Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6692–6701, 2017. doi: 10.1109/CVPR.2017.265 
[17] Brachmann, E., Cavallari, T., and Prisacariu, V. "Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2736–2746, 2023. doi: 10.1109/CVPR52729.2023.00267 
[18] Yang, B., and others. "LiSA: LiDAR Localization with Semantic Awareness". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. doi: 10.1109/CVPR52733.2024.01123 
[19] Abati, G. F., and others. "Panoptic-SLAM: Visual SLAM in Dynamic Environments using Panoptic Segmentation". Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2024. doi: 10.1109/ICRA50011.2024.10611425 
[20] Liu, S., and others. "Semantic-geometry fusion". arXiv preprint arXiv:2501.09876, 2025. 
[21] Yan, S., and others. "Long-term Visual Localization with Mobile Sensors". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. doi: 10.1109/CVPR52729.2023.01639 
[22] Wang, F., and others. "GLACE: Global Local Accelerated Coordinate Encoding". Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. doi: 10.1109/CVPR52733.2024.00492

Downloads: 45000
Visits: 1013024

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.