Semantic visual SLAM in dynamic environment

Human-computer interaction requires accurate localization and effective mapping, while dynamic objects can influence the accuracy of localization and mapping. State-of-the-art SLAM algorithms assume that the environment is static. This paper proposes a new SLAM method that uses mask R-CNN to detect...

Full description

Saved in:
Bibliographic Details
Published inAutonomous robots Vol. 45; no. 4; pp. 493 - 504
Main Authors Wen, Shuhuan, Li, Pengjiang, Zhao, Yongjie, Zhang, Hong, Sun, Fuchun, Wang, Zhe
Format Journal Article
LanguageEnglish
Published New York Springer US 01.05.2021
Springer Nature B.V
Subjects
Algorithms
Artificial Intelligence
Computer Imaging
Control
Engineering
Errors
Localization
Mechatronics
Pattern Recognition and Graphics
Robotics
Robotics and Automation
Segmentation
Semantics
Simultaneous localization and mapping
Vision
Depth error
Semantic SLAM
Reprojection error
Dynamic target detection
Photometric error
Online AccessGet full text

Cover

More Information
Summary:Human-computer interaction requires accurate localization and effective mapping, while dynamic objects can influence the accuracy of localization and mapping. State-of-the-art SLAM algorithms assume that the environment is static. This paper proposes a new SLAM method that uses mask R-CNN to detect dynamic ob-jects in the environment and build a map containing semantic information. In our method, the reprojection error, photometric error and depth error are used to assign a robust weight to each keypoint. Thus, the dynamic points and the static points can be separated, and the geometric segmentation of the dynamic objects can be realized by using the dynamic keypoints. Each pixel is assigned a semantic label to rebuild a semantic map. Finally, our proposed method is tested on the TUM RGB-D dataset, and the experimental results show that the proposed method outperforms state-of-the-art SLAM algorithms in dynamic environments.
ISSN:0929-5593
1573-7527
DOI:10.1007/s10514-021-09979-4