EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments

Fan, Jinlong; Ning, Yipeng; Wang, Jian; Jia, Xiang; Chai, Dashuai; Wang, Xiqi; Xu, Ying

doi:10.3390/rs17101691

Open AccessArticle

EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments

by

Jinlong Fan

¹

,

Yipeng Ning

^1,*,

Jian Wang

²,

Xiang Jia

¹,

Dashuai Chai

¹,

Xiqi Wang

³ and

Ying Xu

⁴

¹

School of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan 250101, China

²

School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China

³

School of Transportation Engineering, Shandong Jianzhu University, Jinan 250101, China

⁴

School of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China

^*

Author to whom correspondence should be addressed.

Remote Sens. 2025, 17(10), 1691; https://doi.org/10.3390/rs17101691

Submission received: 31 March 2025 / Revised: 4 May 2025 / Accepted: 9 May 2025 / Published: 12 May 2025

(This article belongs to the Special Issue Intelligent Perception and Robust Positioning Methods in GNSS-Denied Environments)

Download

Browse Figures

Versions Notes

Abstract

Global navigation satellite systems (GNSSs) exhibit significant performance limitations in signal-deprived environments such as indoor spaces and underground spaces. Although visual SLAM has emerged as a viable solution for ego-motion estimation in GNSS-denied areas, conventional approaches remain constrained by static environment assumptions, resulting in a substantial degradation in accuracy when handling dynamic scenarios. The EMS-SLAM framework combines the geometric constraints and semantics of SLAM to provide a real-time solution for addressing the challenges of robustness and accuracy in dynamic environments. To improve the accuracy of the initial pose, EMS-SLAM employs a feature-matching algorithm based on a graph-cut RANSAC. In addition, a degeneracy-resistant geometric constraint method is proposed, which effectively addresses the degeneracy issues of purely epipolar approaches. Finally, EMS-SLAM combines semantic information with geometric constraints to maintain high accuracy while quickly eliminating dynamic feature points. Experiments were conducted on the public datasets and our collected datasets. The results demonstrate that our method outperformed the current algorithms of SLAM in highly dynamic environments.

Keywords: geometric constraints; semantic information; GC-RANSAC; dynamic environment; GNSS-denied environments

Graphical Abstract

Share and Cite

MDPI and ACS Style

Fan, J.; Ning, Y.; Wang, J.; Jia, X.; Chai, D.; Wang, X.; Xu, Y. EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments. Remote Sens. 2025, 17, 1691. https://doi.org/10.3390/rs17101691

AMA Style

Fan J, Ning Y, Wang J, Jia X, Chai D, Wang X, Xu Y. EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments. Remote Sensing. 2025; 17(10):1691. https://doi.org/10.3390/rs17101691

Chicago/Turabian Style

Fan, Jinlong, Yipeng Ning, Jian Wang, Xiang Jia, Dashuai Chai, Xiqi Wang, and Ying Xu. 2025. "EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments" Remote Sensing 17, no. 10: 1691. https://doi.org/10.3390/rs17101691

APA Style

Fan, J., Ning, Y., Wang, J., Jia, X., Chai, D., Wang, X., & Xu, Y. (2025). EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments. Remote Sensing, 17(10), 1691. https://doi.org/10.3390/rs17101691

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

EMS-SLAM: Dynamic RGB-D SLAM with Semantic-Geometric Constraints for GNSS-Denied Environments

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI