MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity
arXiv:2112.06539 · doi:10.1109/LRA.2021.3136863
Abstract
The 3D LiDAR place recognition aims to estimate a coarse localization in a previously seen environment based on a single scan from a rotating 3D LiDAR sensor. The existing solutions to this problem include hand-crafted point cloud descriptors (e.g., ScanContext, M2DP, LiDAR IRIS) and deep learning-based solutions (e.g., PointNetVLAD, PCAN, LPDNet, DAGC, MinkLoc3D), which are often only evaluated on accumulated 2D scans from the Oxford RobotCar dataset. We introduce MinkLoc3D-SI, a sparse convolution-based solution that utilizes spherical coordinates of 3D points and processes the intensity of 3D LiDAR measurements, improving the performance when a single 3D LiDAR scan is used. Our method integrates the improvements typical for hand-crafted descriptors (like ScanContext) with the most efficient 3D sparse convolutions (MinkLoc3D). Our experiments show improved results on single scans from 3D LiDARs (USyd Campus dataset) and great generalization ability (KITTI dataset). Using intensity information on accumulated 2D scans (RobotCar Intensity dataset) improves the performance, even though spherical representation doesn't produce a noticeable improvement. As a result, MinkLoc3D-SI is suited for single scans obtained from a 3D LiDAR, making it applicable in autonomous vehicles.
References in corpus (7)
- In Defense of the Triplet Loss for Person Re-Identification
- Learning Descriptors for Object Recognition and 3D Pose Estimation
- Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
- OverlapNet: Loop Closing for LiDAR-based SLAM
- SegMap: Segment-based mapping and localization using data-driven descriptors
- Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
- AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition