I-LOAM: Intensity Enhanced LiDAR Odometry and Mapping

In this paper, we introduce an extension to the existing LiDAR Odometry and Mapping (LOAM) [1] by additionally considering LiDAR intensity. In an urban environment, planar structures from buildings and roads often introduce ambiguity in a certain direction. Incorporation of the intensity value to the cost function prevents divergence occurence from this structural ambiguity, thereby yielding better odometry and mapping in terms of accuracy. Specifically, we have updated the edge and plane point correspondence search to include intensity. This simple but effective strategy shows meaningful improvement over the existing LOAM. The proposed method is validated using the KITTI dataset.

[1]  Jinyong Jeong,et al.  LiDAR Intensity Calibration for Road Marking Extraction , 2018, 2018 15th International Conference on Ubiquitous Robots (UR).

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

[3]  Youngchul Kim,et al.  A new 3D space syntax metric based on 3D isovist capture in urban space using remote sensing technology , 2019, Comput. Environ. Urban Syst..

[4]  Ji Zhang,et al.  A real-time method for depth enhanced visual odometry , 2017, Auton. Robots.

[5]  Ji Zhang,et al.  Low-drift and real-time lidar odometry and mapping , 2017, Auton. Robots.

[6]  Federico Tombari,et al.  Unique Signatures of Histograms for Local Surface Description , 2010, ECCV.

[7]  Denis Wolf,et al.  Road marking detection using LIDAR reflective intensity data and its application to vehicle localization , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[8]  Sebastian Thrun,et al.  Unsupervised Calibration for Multi-beam Lasers , 2010, ISER.

[9]  Abel Gawel,et al.  Local Descriptor for Robust Place Recognition Using LiDAR Intensity , 2018, IEEE Robotics and Automation Letters.

[10]  Yeong Sang Park,et al.  DVL-SLAM: sparse depth enhanced direct visual-LiDAR SLAM , 2019, Autonomous Robots.

[11]  Giorgio Grisetti,et al.  NICP: Dense normal based point cloud registration , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).