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
[31]   Real-time Non-rigid Reconstruction using an RGB-D Camera [J].
Zollhoefer, Michael ;
Niessner, Matthias ;
Izadi, Shahram ;
Rehmann, Christoph ;
Zach, Christopher ;
Fisher, Matthew ;
Wu, Chenglei ;
Fitzgibbon, Andrew ;
Loop, Charles ;
Theobalt, Christian ;
Stamminger, Marc .
ACM TRANSACTIONS ON GRAPHICS, 2014, 33 (04)
[32]   Effective Background Model-Based RGB-D Dense Visual Odometry in a Dynamic Environment [J].
Kim, Deok-Hwa ;
Kim, Jong-Hwan .
IEEE TRANSACTIONS ON ROBOTICS, 2016, 32 (06) :1565-1573
[33]   RGB-D Inertial Odometry for a Resource-Restricted Robot in Dynamic Environments [J].
Liu, Jianheng ;
Li, Xuanfu ;
Liu, Yueqian ;
Chen, Haoyao .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) :9573-9580
[34]   Real-Time RGB-D Camera Relocalization [J].
Glocker, Ben ;
Izadi, Shahram ;
Shotton, Jamie ;
Criminisi, Antonio .
2013 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR) - SCIENCE AND TECHNOLOGY, 2013, :173-179
[35]   Robust RGB-D SLAM in Dynamic Environments for Autonomous Vehicles [J].
Ji, Tete ;
Yuan, Shenghai ;
Xie, Lihua .
2022 17TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV), 2022, :665-671
[36]   Feature Regions Segmentation based RGB-D Visual Odometry in Dynamic Environment [J].
Zhang, Yu ;
Dai, Weichen ;
Peng, Zhen ;
Li, Ping ;
Fang, Zheng .
IECON 2018 - 44TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2018, :5648-5655
[37]   A Robust and Real-Time RGB-D SLAM Method with Dynamic Point Recognition and Depth Segmentation Optimization [J].
Chen, Shuaixin ;
Gan, Baolin ;
Zhang, Congxuan ;
Chen, Zhen ;
Lu, Ke ;
Lu, Feng .
PATTERN RECOGNITION AND COMPUTER VISION, PT IX, PRCV 2024, 2025, 15039 :247-261
[38]   KinectScenes: Robust Real-time RGB-D Fusion for Animal Behavioural Monitoring [J].
Jeya, Logan ;
Zelek, John .
2016 13TH CONFERENCE ON COMPUTER AND ROBOT VISION (CRV), 2016, :383-390
[39]   Motion removal for reliable RGB-D SLAM in dynamic environments [J].
Sun, Yuxiang ;
Liu, Ming ;
Meng, Max Q. -H. .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2018, 108 :115-128
[40]   RGB-D Visual Odometry Based on Features of Planes and Line Segments in Indoor Environments [J].
Dong, Xingliang ;
Yuan, Jing ;
Huang, Shuzi ;
Yang, Shaokun ;
Zhang, Xuebo ;
Sun, Fengchi ;
Huang, Yalou .
Jiqiren/Robot, 2018, 40 (06) :921-932