LiDAR Odometry by Deep Learning-Based Feature Points with Two-Step Pose Estimation
Open Access
- 9 June 2022
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 14 (12) , 2764
Abstract
An accurate ego-motion estimation solution is vital for autonomous vehicles. LiDAR is widely adopted in self-driving systems to obtain depth information directly and eliminate the influence of changing illumination in the environment. In LiDAR odometry, the lack of descriptions of feature points as well as the failure of the assumption of uniform motion may cause mismatches or dilution of precision in navigation. In this study, a method to perform LiDAR odometry utilizing a bird’s eye view of LiDAR data combined with a deep learning-based feature point is proposed. Orthographic projection is applied to generate a bird’s eye view image of a 3D point cloud. Thereafter, an R2D2 neural network is employed to extract keypoints and compute their descriptors. Based on those keypoints and descriptors, a two-step matching and pose estimation is designed to keep these feature points tracked over a long distance with a lower mismatch ratio compared to the conventional strategy. In the experiment, the evaluation of the proposed algorithm on the KITTI training dataset demonstrates that the proposed LiDAR odometry can provide more accurate trajectories compared with the handcrafted feature-based SLAM (Simultaneous Localization and Mapping) algorithm. In detail, a comparison of the handcrafted descriptors is demonstrated. The difference between the RANSAC (Random Sample Consensus) algorithm and the two-step pose estimation is also demonstrated experimentally. In addition, the data collected by Velodyne VLP-16 is also evaluated by the proposed solution. The low-drift positioning RMSE (Root Mean Square Error) of 4.70 m from approximately 5 km mileage shown in the result indicates that the proposed algorithm has generalization performance on low-resolution LiDAR.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2020YFB0505803, 41974024)
- National Natural Science Foundation of China (2020YFB0505803, 41974024)
This publication has 37 references indexed in Scilit:
- GNSS/INS/LiDAR-SLAM Integrated Navigation System Based on Graph OptimizationRemote Sensing, 2019
- Making Sense of Spatio-Temporal Preserving Representations for EEG-Based Human Intention RecognitionIEEE Transactions on Cybernetics, 2019
- LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain2018
- L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space2017
- An Adaptive Semisupervised Feature Analysis for Video Semantic RecognitionIEEE Transactions on Cybernetics, 2017
- LIFT: Learned Invariant Feature Transform2016
- NICP: Dense normal based point cloud registration2015
- ORB: An efficient alternative to SIFT or SURF2011
- 3D is here: Point Cloud Library (PCL)2011
- Object recognition from local scale-invariant features1999