3D street pole-like object detection and recognition for self-drive car localization

Unprecedented resources have been devoted for autonomous driving worldwide, and Taiwan is no exception. Self-drive bus trials are undergoing among major cities including Taipei, Taoyuan, Taichung and Kaoshiung. One of the most important tasks for self-drive bus navigation is to localize itself based on landmarks of pre-built 3D semantic maps. This paper investigates street pole-like object detection and recognition from the 3D point cloud data. Both traditional covariance and new AI-based deep learning techniques are used to evaluate the results.

[1]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Enoc Sanz-Ablanedo,et al.  Automatic Detection and Classification of Pole-Like Objects for Urban Cartography Using Mobile Laser Scanning Data , 2017, Sensors.

[3]  Edwin Olson,et al.  Fast and robust 3D feature extraction from sparse point clouds , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Ryan M. Eustice,et al.  Fast LIDAR localization using multiresolution Gaussian mixture maps , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.