Structure Reconstruction Using Ray-Point-Ray Features: Representation and Camera Pose Estimation

被引:2
|
作者
He, Yijia
Liu, Xiangyue [1 ]
Liu, Xiao [2 ]
Zhao, Ji
机构
[1] Beihang Univ, Sch Software, Beijing, Peoples R China
[2] Megvii Face Technol Inc, Beijing, Peoples R China
来源
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) | 2021年
关键词
CORRESPONDENCES;
D O I
10.1109/ICRA48506.2021.9561283
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Straight line features have been increasingly utilized in visual SLAM and 3D reconstruction systems. The straight lines' parameterization, parallel constraint, and co-planar constraint are studied in many recent works. In this paper, we explore the novel intersection constraint of straight lines for structure reconstruction. First, a minimum parameterized representation of ray-point-ray (RPR) structures is proposed to represent the intersection of two straight lines in the 3D space. Second, an efficient solver is designed for the camera pose estimation, which leverages the perpendicularity and intersection of straight lines. Third, we build a stereo visual odometry based on RPR features and evaluate it on the simulation and real datasets. The experimental results verify that the intersection constraints from RPR can effectively improve the accuracy and efficiency of line-based SLAM and reconstruction system.
引用
收藏
页码:5388 / 5394
页数:7
相关论文
共 2 条
  • [1] Pose and Focal Length Estimation Using a Point and a Line With Known Camera Position
    Guo, Kai
    Cao, Rui
    Zhang, Zhixiang
    Zhou, Xin
    Yue, Chenyang
    Liu, Boyu
    IEEE ACCESS, 2023, 11 : 102471 - 102482
  • [2] An efficient and globally optimal method for camera pose estimation using line features
    Yu, Qida
    Xu, Guili
    Cheng, Yuehua
    MACHINE VISION AND APPLICATIONS, 2020, 31 (06)