Accurate and Robust Object SLAM with 3D Quadric Landmark Reconstruction in Outdoors

Rui Tian, Yunzhou Zhang, Yonghui Feng, Linghao Yang, Zhenzhong Cao, Sonya Coleman, Dermot Kerr

Research output: Contribution to journalArticlepeer-review

59 Downloads (Pure)

Abstract

Object-oriented SLAM is a popular technology in autonomous driving and robotics. In this letter, we propose a stereo visual SLAM with a robust quadric landmark representation method.The system consists of four components, including deep learning detection, quadric landmark initialization, object data association and object pose optimization. State-of-the-art quadric-based SLAM algorithms always face observation-related problems and are sensitive to observation noise, which limits their application in outdoor scenes. To solve this problem, we propose a quadric initialization method based on the separation of the quadric parameters method, which improves the robustness to observation noise. The sufficient object data association algorithm and object-oriented optimization with multiple cues enable a highly accurate object pose estimation that is robust to local observations. Experimental results show that the proposed system is more robust to observation noise and significantly outperforms current state-of-the-art methods in outdoor environments. In addition, the proposed system demonstrates real-time performance.

Original languageEnglish
Pages (from-to)1534-1541
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume7
Issue number2
Early online date23 Dec 2021
DOIs
Publication statusPublished - 30 Apr 2022

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grants 61973066 and 61471110, in part by the Major Science and Technology Projects of Liaoning Province under Grant 2021JH1/10400049, in part by the Fundation of Key Laboratory of Aerospace System Simulation under Grant 6142002200301, in part by the Fundation of Key Laboratory of Equipment Reliability under Grant WD2C20205500306, and in part by the Major Science and Technology Innovation Engineering Projects of Shandong Province under Grant 2019JZZY010128.

Publisher Copyright:
© 2016 IEEE.

Keywords

  • Cameras
  • Ellipsoids
  • Localization
  • Optimization
  • Semantics
  • Simultaneous localization and mapping
  • SLAM
  • Three-dimensional displays
  • Vision-Based Navigation
  • Visualization
  • Vision-based navigation

Fingerprint

Dive into the research topics of 'Accurate and Robust Object SLAM with 3D Quadric Landmark Reconstruction in Outdoors'. Together they form a unique fingerprint.

Cite this