Egomotion Estimation Under Planar Motion with an RGB-D Camera

In this paper, we propose a method for egomotion estimation of an indoor mobile robot under planar motion with an RGB-D camera. Our approach mainly deals with the corridor-like structured scenarios and uses the prior knowledge of the environment: when at least one vertical plane is detected using the depth data, egomotion is estimated with one normal of the vertical plane and one point; when there are no vertical planes, a 2-point homography-based algorithm using only point correspondences is presented for the egomotion estimation. The proposed method then is used in a frame-to-frame visual odometry framework. We evaluate our algorithm on the synthetic data and show the application on the real-world data. The experiments show that the proposed approach is efficient and robust enough for egomotion estimation in the Manhattan-like environments compared with the state-of-the-art methods.

[1]  Frederik Schaffalitzky,et al.  Four Points in Two or Three Calibrated Views: Theory and Practice , 2006, International Journal of Computer Vision.

[2]  Richard I. Hartley,et al.  In defence of the 8-point algorithm , 1995, Proceedings of IEEE International Conference on Computer Vision.

[3]  Francesc Moreno-Noguer,et al.  Efficient monocular pose estimation for complex 3D models , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[4]  H. Jin Kim,et al.  Visual Odometry with Drift-Free Rotation Estimation Using Indoor Scene Regularities , 2017, BMVC.

[5]  Daniel Cremers,et al.  Online Photometric Calibration of Auto Exposure Video for Realtime Visual Odometry and SLAM , 2017, IEEE Robotics and Automation Letters.

[6]  Michael Kaess,et al.  Simultaneous localization and mapping with infinite planes , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Yaser Sheikh,et al.  Real-time scalable 6DOF pose estimation for textureless objects , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[9]  Zuzana Kukelova,et al.  Polynomial Eigenvalue Solutions to the 5-pt and 6-pt Relative Pose Problems , 2008, BMVC.

[10]  Michael Gassner,et al.  SVO: Semidirect Visual Odometry for Monocular and Multicamera Systems , 2017, IEEE Transactions on Robotics.

[11]  Qingxuan Jia,et al.  Multiple Maps for the Feature-based Monocular SLAM System , 2019, J. Intell. Robotic Syst..

[12]  Jana Kosecka,et al.  Dense piecewise planar RGB-D SLAM for indoor environments , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jörg Stückler,et al.  Omnidirectional DSO: Direct Sparse Odometry With Fisheye Cameras , 2018, IEEE Robotics and Automation Letters.

[15]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[16]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.

[17]  Pascal Vasseur,et al.  Homography Based Egomotion Estimation with a Common Direction , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  James R. Bergen,et al.  Visual odometry , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[19]  Daniel Cremers,et al.  Direct Sparse Odometry , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Shoufeng Tang,et al.  Vision Odometer Based on RGB-D Camera , 2018, 2018 International Conference on Robots & Intelligent System (ICRIS).

[21]  Vincent Lepetit,et al.  Approximated Relative Pose Solvers for Efficient Camera Motion Estimation , 2014, ECCV Workshops.

[22]  Andrew Calway,et al.  Absolute pose estimation using multiple forms of correspondences from RGB-D frames , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Hongdong Li,et al.  Five-Point Motion Estimation Made Easy , 2006, 18th International Conference on Pattern Recognition (ICPR'06).