Title | Line Flow Based Simultaneous Localization and Mapping |
Authors | Wang, Qiuyuan Yan, Zike Wang, Junqiu Xue, Fei Ma, Wei Zha, Hongbin |
Affiliation | Peking Univ, Key Lab Machine Percept, Minister Educ, Beijing 100871, Peoples R China AVIC, Beijing Changcheng Aeronaut Measurement & Control, Beijing 100176, Peoples R China Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China |
Keywords | STRUCTURE-FROM-MOTION SEGMENT DETECTOR EFFICIENT REPRESENTATION GRAPH |
Issue Date | Oct-2021 |
Publisher | IEEE TRANSACTIONS ON ROBOTICS |
Abstract | In this article, we propose a visual simultaneous localization and mapping (SLAM) method by predicting and updating line flows that represent sequential 2-D projections of 3-D line segments. While feature-based SLAM methods have achieved excellent results, they still face problems in challenging scenes containing occlusions, blurred images, and repetitive textures. To address these problems, we leverage a line flow to encode the coherence of line segment observations of the same 3-D line along the temporal dimension, which has been neglected in prior SLAM systems. Thanks to this line flow representation, line segments in a new frame can be predicted according to their corresponding 3-D lines and their predecessors along the temporal dimension. We create, update, merge, and discard line flows on-the-fly. We model the proposed line flow based SLAM (LF-SLAM) using a Bayesian network. Extensive experimental results demonstrate that the proposed LF-SLAM method achieves state-of-the-art results due to the utilization of line flows. Specifically, LF-SLAM obtains good localization and mapping results in challenging scenes with occlusions, blurred images, and repetitive textures. |
URI | http://hdl.handle.net/20.500.11897/626305 |
ISSN | 1552-3098 |
DOI | 10.1109/TRO.2021.3061403 |
Indexed | SCI(E) |
Appears in Collections: | 机器感知与智能教育部重点实验室 |