Robust Improvement in 3D Object Landmark Inference for Semantic Mapping

Lin，Xubin1; Yang，Yirui1; He，Li1; Chen，Weinan2; Guan，Yisheng1; Zhang，Hong2

10.1109/ICRA48506.2021.9561596

2021

IEEE International Conference on Robotics and Automation (ICRA)

1050-4729

2577-087X

978-1-7281-9078-5

Proceedings - IEEE International Conference on Robotics and Automation

2021-May

13011-13017

MAY 30-JUN 05, 2021

null,Xian,PEOPLES R CHINA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Recent works on semantic Simultaneous Localization and Mapping (SLAM) utilizing object landmarks have shown superiority in terms of robustness and accuracy in tracking and localization. 3D object landmarks represented by a cubic or quadric surface are inferred from 2D object bounding boxes which are typically captured from multiple views by an object detector. Nevertheless, bounding box noises and small camera baseline may lead to an inaccurate 3D object landmark inference. Inspired by the dual quadric enveloping property, in this work, we introduce the horizontal support assumption to constrain rotation w.r.t. roll and pitch for a quadric representation. As the result, we reduce the number of quadric parameters and narrow down the solution space, and ultimately produce a relatively accurate inference. Extensive experimental evaluations under both simulated and real scenarios are conducted in this paper. Quantitative results demonstrate that our approach outperforms the state-of-the-art.

Dual quadric Object reconstruction Semantic mapping SLAM

通讯

英语

CPCI-S ; EI

National Natural Science Foundation of China[61673125];National Natural Science Foundation of China[61703115];

Automation & Control Systems ; Robotics

Automation & Control Systems ; Robotics

WOS:000771405404111

20220911738739

Computer vision ; Image reconstruction ; Mapping ; Object detection ; Robotics

Surveying:405.3 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Robotics:731.5 ; Vision:741.2

2-s2.0-85125502884

Scopus

1.The Biomimetic and Intelligent Robotics Lab (BIRL),Guangdong University of Technology,Guangzhou,510006,China
2.The Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,China

Lin，Xubin,Yang，Yirui,He，Li,et al. Robust Improvement in 3D Object Landmark Inference for Semantic Mapping[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:13011-13017.