Monocular Localization in Feature-Annotated 3D Polygon Maps

Localization in six degrees of freedom is becoming increasingly relevant, especially in indoor environments where GPS is not available. To localize autonomous vehicles like UAVs in such areas, reliable methods for self-localization with low-weight sensors are required. In this paper, we present an approach to precisely localize systems with monocular cameras in polygonal 3D maps annotated with keypoints and feature descriptors computed from LiDAR data and associated reference images. Our contribution consists of offline map computation from high resolution 3D point clouds with corresponding reference images as well as online localization within these maps using low cost sensors. During localization, features extracted from the vehicle’s camera image stream are matched against the reference map. The proposed method is capable of real-time localization and suitable for precise global localization. The evaluation shows comparable results to state of the art with high re-localization accuracy.

[1]  Sven Behnke,et al.  Efficient Continuous-Time SLAM for 3D Lidar-Based Online Mapping , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Marcelo H. Ang,et al.  2D3D-Matchnet: Learning To Match Keypoints Across 2D Image And 3D Point Cloud , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[3]  Joachim Hertzberg,et al.  Towards Real Time Robot 6D Localization in a Polygonal Indoor Map Based on 3D ToF Camera Data , 2010 .

[4]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[5]  Joachim Hertzberg,et al.  Continuous Shortest Path Vector Field Navigation on 3D Triangular Meshes for Mobile Robots , 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[7]  Roberto Torres,et al.  Ray casting using a roped BVH with CUDA , 2009, SCCG.

[8]  Yahya Zweiri,et al.  Feature-based visual simultaneous localization and mapping: a survey , 2020, SN Applied Sciences.

[9]  Thomas Wiemann,et al.  A File Structure and Reference Data Set for High Resolution Hyperspectral 3D Point Clouds , 2019, IFAC-PapersOnLine.

[10]  Wolfgang Hess,et al.  Real-time loop closure in 2D LIDAR SLAM , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Roland Siegwart,et al.  The EuRoC micro aerial vehicle datasets , 2016, Int. J. Robotics Res..

[12]  David G. Lowe,et al.  Scalable Nearest Neighbor Algorithms for High Dimensional Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Long Quan,et al.  Linear N-Point Camera Pose Determination , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Jean-Michel Morel,et al.  ASIFT: An Algorithm for Fully Affine Invariant Comparison , 2011, Image Process. Line.

[15]  Dorian Gálvez-López,et al.  Bags of Binary Words for Fast Place Recognition in Image Sequences , 2012, IEEE Transactions on Robotics.

[16]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

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

[18]  Adrien Bartoli,et al.  Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces , 2013, BMVC.

[19]  Joachim Hertzberg,et al.  Real Time Texture Generation in Optimized Large-Scale Polygon Meshes with KinectFusion , 2016 .

[20]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[21]  Tomas Akenine-Möller,et al.  Fast, Minimum Storage Ray-Triangle Intersection , 1997, J. Graphics, GPU, & Game Tools.

[22]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[23]  Ji Zhang,et al.  LOAM: Lidar Odometry and Mapping in Real-time , 2014, Robotics: Science and Systems.

[24]  Joachim Hertzberg,et al.  An Extended Evaluation of Open Source Surface Reconstruction Software for Robotic Applications , 2015, J. Intell. Robotic Syst..

[25]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[26]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[27]  V. Lepetit,et al.  EPnP: An Accurate O(n) Solution to the PnP Problem , 2009, International Journal of Computer Vision.

[28]  Joachim Hertzberg,et al.  Surface Reconstruction from Arbitrarily Large Point Clouds , 2018, 2018 Second IEEE International Conference on Robotic Computing (IRC).

[29]  Doug Baldwin.  Fast Ray-Triangle Intersections by Coordinate Transformation , 2016 .