TY - GEN
T1 - DOC-SLAM
T2 - 2021 International Conference on Automation, Robotics and Applications, ICARA 2021
AU - Lyu, Lin
AU - Ding, Yan
AU - Yuan, Yating
AU - Zhang, Yutong
AU - Liu, Jinpeng
AU - Li, Jiaxin
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/2/4
Y1 - 2021/2/4
N2 - To improve the accuracy of estimating camera trajectory in dynamic scenes, this paper proposes Dynamic Object Culling SLAM(DOC-SLAM), a stereo SLAM system that achieves good performance by culling actual moving objects in highly dynamic environments. DOC-SLAM combines the semantic information from panoptic segmentation with the point features from optical flow together to detect potential moving objects. And a moving consistency check module is designed to determine and remove the feature points in objects which are in motion so as to accomplish dynamic objects culling. Besides, for enhancing the robustness of our system, we devise a key point supplement strategy to provide sufficient and reliable key points for tracking. Meanwhile, the trajectory and landmarks are generated for localization and mapping of robots. The experimental evaluation on public datasets demonstrates that our DOC-SLAM can fit highly dynamic scenes.
AB - To improve the accuracy of estimating camera trajectory in dynamic scenes, this paper proposes Dynamic Object Culling SLAM(DOC-SLAM), a stereo SLAM system that achieves good performance by culling actual moving objects in highly dynamic environments. DOC-SLAM combines the semantic information from panoptic segmentation with the point features from optical flow together to detect potential moving objects. And a moving consistency check module is designed to determine and remove the feature points in objects which are in motion so as to accomplish dynamic objects culling. Besides, for enhancing the robustness of our system, we devise a key point supplement strategy to provide sufficient and reliable key points for tracking. Meanwhile, the trajectory and landmarks are generated for localization and mapping of robots. The experimental evaluation on public datasets demonstrates that our DOC-SLAM can fit highly dynamic scenes.
KW - SLAM system
KW - dynamic object culling
KW - panoptic segmentation
KW - trajectory estimation
UR - http://www.scopus.com/inward/record.url?scp=85103738720&partnerID=8YFLogxK
U2 - 10.1109/ICARA51699.2021.9376418
DO - 10.1109/ICARA51699.2021.9376418
M3 - Conference contribution
AN - SCOPUS:85103738720
T3 - 2021 International Conference on Automation, Robotics and Applications, ICARA 2021
SP - 258
EP - 262
BT - 2021 International Conference on Automation, Robotics and Applications, ICARA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 February 2021 through 6 February 2021
ER -