Real-Time Point Cloud Alignment for Vehicle Localization in a High Resolution 3D Map

In this paper we introduce a Lidar based real time and accurate self localization approach for self driving vehicles (SDV) in high resolution 3D point cloud maps of the environment obtained through Mobile Laser Scanning (MLS). Our solution is able to robustly register the sparse point clouds of the SDVs to the dense MLS point cloud data, starting from a GPS based initial position estimation of the vehicle. The main steps of the method are robust object extraction and transformation estimation based on multiple keypoints extracted from the objects, and additional semantic information derived from the MLS based map. We tested our approach on roads with heavy traffic in the downtown of a large city with large GPS positioning errors, and showed that the proposed method enhances the matching accuracy with an order of magnitude. Comparative tests are provided with various keypoint selection strategies, and against a state-of-the-art technique.

[1]  Cheng Wang,et al.  Automated Detection of Three-Dimensional Cars in Mobile Laser Scanning Point Clouds Using DBM-Hough-Forests , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Xiaolong Hu,et al.  Autonomous Driving in the iCity—HD Maps as a Key Challenge of the Automotive Industry , 2016 .

[3]  Tim Bailey,et al.  Scan segments matching for pairwise 3D alignment , 2012, 2012 IEEE International Conference on Robotics and Automation.

[4]  Clément Mallet,et al.  TRAJECTORY-BASED REGISTRATION OF 3D LIDAR POINT CLOUDS ACQUIRED WITH A MOBILE MAPPING SYSTEM , 2012 .

[5]  Zhengyou Zhang,et al.  Iterative point matching for registration of free-form curves and surfaces , 1994, International Journal of Computer Vision.

[6]  Anil K. Jain,et al.  A Real-Time Matching System for Large Fingerprint Databases , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Hao Men,et al.  Color point cloud registration with 4D ICP algorithm , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  A. Ijspeert,et al.  Environmental monitoring using autonomous vehicles: a survey of recent searching techniques. , 2017, Current Opinion in Biotechnology.

[9]  Csaba Benedek,et al.  Fast 3-D Urban Object Detection on Streaming Point Clouds , 2014, ECCV Workshops.

[10]  Martin Magnusson,et al.  The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection , 2009 .

[11]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[12]  Markus Maurer,et al.  Map-relative localization in lane-level maps for ADAS and autonomous driving , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[13]  Yongwan Park,et al.  Map Building Based on Sensor Fusion for Autonomous Vehicle , 2014, 2014 11th International Conference on Information Technology: New Generations.

[14]  Mohammed Bennamoun,et al.  On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes , 2009, International Journal of Computer Vision.

[15]  Csaba Benedek,et al.  Crossmodal point cloud registration in the Hough space for mobile laser scanning data , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[16]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[17]  Nicolas David,et al.  IMPROVING 3D LIDAR POINT CLOUD REGISTRATION USING OPTIMAL NEIGHBORHOOD KNOWLEDGE , 2012 .

[18]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[19]  Csaba Benedek,et al.  3D CNN based phantom object removing from mobile laser scanning data , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).