Journal
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
Volume 10, Issue 3, Pages -Publisher
MDPI
DOI: 10.3390/ijgi10030163
Keywords
RGB-D; Simultaneous Localization and Mapping; dynamic scenes; deep learning; target detection; K-means
Funding
- Postgraduate Research and Practice Innovation Program of Jiangsu Province [KYCX20_0485]
- Fundamental Research Funds for the Central Universities [B200203106]
- National Natural Science Foundation of China [41901401]
Ask authors/readers for more resources
The paper introduces a new RGB-D dynamic SLAM method, PLD-SLAM, for dynamic scenes, combining point and line features for better performance. Through the integration of deep learning, clustering algorithm, and consistency check strategies, dynamic features are effectively detected and filtered to improve practicality. The use of point and line features in the optimization model contributes to higher accuracy in camera pose estimation, showcasing comparable or better performances in dynamic scenes compared to existing dynamic SLAM methods.
RGB-D SLAM (Simultaneous Localization and Mapping) generally performs smoothly in a static environment. However, in dynamic scenes, dynamic features often cause wrong data associations, which degrade accuracy and robustness. To address this problem, in this paper, a new RGB-D dynamic SLAM method, PLD-SLAM, which is based on point and line features for dynamic scenes, is proposed. First, to avoid under-over segmentation caused by deep learning, PLD-SLAM combines deep learning for semantic information segmentation with the K-Means clustering algorithm considering depth information to detect the underlying dynamic features. Next, two consistency check strategies are utilized to check and filter out the dynamic features more reasonably. Then, to obtain a better practical performance, point and line features are utilized to calculate camera pose in the dynamic SLAM, which is also different from most published dynamic SLAM algorithms based merely on point features. The optimization model with point and line features is constructed and utilized to calculate the camera pose with higher accuracy. Third, enough experiments on the public TUM RGB-D dataset and the real-world scenes are conducted to verify the location accuracy and performance of PLD-SLAM. We compare our experimental results with several state-of-the-art dynamic SLAM methods in terms of average localization errors and the visual difference between the estimation trajectories and the ground-truth trajectories. Through the comprehensive comparisons with these dynamic SLAM schemes, it can be fully demonstrated that PLD-SLAM can achieve comparable or better performances in dynamic scenes. Moreover, the feasibility of camera pose estimation based on both point features and line features has been proven by the corresponding experiments from a comparison with our proposed PLD-SLAM only based on point features.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available