Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model

被引:0
作者
Lee, Sangil [1 ]
Son, Clark Youngdong [1 ]
Kim, H. Jin [1 ]
机构
[1] Seoul Natl Univ, Dept Mech & Aerosp Engn, Automat & Syst Res Inst, Seoul 08826, South Korea
来源
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2019年
关键词
D O I
10.1109/iros40897.2019.8968208
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the paper, we propose a robust real-time visual odometry in dynamic environments via rigid-motion model updated by scene flow. The proposed algorithm consists of spatial motion segmentation and temporal motion tracking. The spatial segmentation first generates several motion hypotheses by using a grid-based scene flow and clusters the extracted motion hypotheses, separating objects that move independently of one another. Further, we use a dual-mode motion model to consistently distinguish between the static and dynamic parts in the temporal motion tracking stage. Finally, the proposed algorithm estimates the pose of a camera by taking advantage of the region classified as static parts. In order to evaluate the performance of visual odometry under the existence of dynamic rigid objects, we use self-collected dataset containing RGB-D images and motion capture data for ground-truth. We compare our algorithm with state-of-the-art visual odometry algorithms. The validation results suggest that the proposed algorithm can estimate the pose of a camera robustly and accurately in dynamic environments.
引用
收藏
页码:6891 / 6898
页数:8
相关论文
共 50 条
[41]   Real-Time RGB-D Visual Tracking With Scale Estimation and Occlusion Handling [J].
Leng, Jiaxu ;
Liu, Ying .
IEEE ACCESS, 2018, 6 :24256-24263
[42]   A Hybrid Real-Time Visual Tracking Using Compressive RGB-D Features [J].
Zhao, Mengyuan ;
Luo, Heng ;
Tafti, Ahmad P. ;
Lin, Yuanchang ;
He, Guotian .
ADVANCES IN VISUAL COMPUTING, PT I (ISVC 2015), 2015, 9474 :561-573
[43]   Robust Rigid Point Cloud Registration via RGB-D Images [J].
Zhong, Saishang ;
Li, Yanlei ;
Liu, Zheng ;
Xie, Zhong ;
Chen, Jianguo ;
Wang, Weiming ;
Liu, Xiuping .
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2022, 34 (01) :25-35
[44]   Real-time 3-D Mapping for Indoor Environments using RGB-D Cameras [J].
Chen, Liang-Chia ;
Nguyen Van Thai .
ADVANCED MANUFACTURING FOCUSING ON MULTI-DISCIPLINARY TECHNOLOGIES, 2012, 579 :435-444
[45]   Improved Real-Time Odometry Estimation Method for Incremental RGB-D Mapping by Fusing IMU Data [J].
Guo, Ruibin ;
Zhou, Dongxiang ;
Peng, Keju ;
Fan, Weihong ;
Liu, Yunhui .
PROCEEDINGS OF THE 2016 12TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2016, :2991-2995
[46]   SSF-SLAM: Real-Time RGB-D Visual SLAM for Complex Dynamic Environments Based on Semantic and Scene Flow Geometric Information [J].
Zhang, Ziqi ;
Song, Yong ;
Pang, Bao ;
Yuan, Xianfeng ;
Xu, Qingyang ;
Xu, Xiaolong .
IEEE Transactions on Instrumentation and Measurement, 2025, 74
[47]   SSF-SLAM: Real-Time RGB-D Visual SLAM for Complex Dynamic Environments Based on Semantic and Scene Flow Geometric Information [J].
Zhang, Ziqi ;
Song, Yong ;
Pang, Bao ;
Yuan, Xianfeng ;
Xu, Qingyang ;
Xu, Xiaolong .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
[48]   Nonparametric Statistical and Clustering Based RGB-D Dense Visual Odometry in a Dynamic Environment [J].
Zhou, Wugen ;
Peng, Xiaodong ;
Wang, Haijiao ;
Liu, Bo .
3D RESEARCH, 2019, 10 (02)
[49]   SlamDunk: Affordable Real-Time RGB-D SLAM [J].
Fioraio, Nicola ;
Di Stefano, Luigi .
COMPUTER VISION - ECCV 2014 WORKSHOPS, PT I, 2015, 8925 :401-414
[50]   Visual Odometry Algorithm Using an RGB-D Sensor and IMU in a Highly Dynamic Environment [J].
Kim, Deok-Hwa ;
Han, Seung-Beom ;
Kim, Jong-Hwan .
ROBOT INTELLIGENCE TECHNOLOGY ANDAPPLICATIONS 3, 2015, 345 :11-26