NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation
Authors:
- 30 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5654-5660
Abstract
3D point cloud-based place recognition is highly demanded by autonomous driving in GPS-challenged environments and serves as an essential component (i.e. loop-closure detection) in lidar-based SLAM systems. This paper proposes a novel approach, named NDT-Transformer, for real-time and large-scale place recognition using 3D point clouds. Specifically, a 3D Normal Distribution Transform (NDT) representation is employed to condense the raw, dense 3D point cloud as probabilistic distributions (NDT cells) to provide the geometrical shape description. Then a novel NDT-Transformer network learns a global descriptor from a set of 3D NDT cell representations. Benefiting from the NDT representation and NDT-Transformer network, the learned global descriptors are enriched with both geometrical and contextual information. Finally, descriptor retrieval is achieved using a query-database for place recognition. Compared to the state-of-the-art methods, the proposed approach achieves an improvement of 7.52% on average top 1 recall and 2.73% on average top 1% recall on the Oxford Robotcar benchmark.Keywords
All Related Versions
Funding Information
- Royal Society
This publication has 23 references indexed in Scilit:
- Semi-supervised 3D place categorisation by descriptor clustering2017
- SegMatch: Segment based place recognition in 3D point clouds2017
- M2DP: A novel 3D point cloud descriptor and its application in loop closure detection2016
- 1 year, 1000 km: The Oxford RobotCar datasetThe International Journal of Robotics Research, 2016
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition2016
- IRON: A fast interest point descriptor for robust NDT-map matching and its application to robot localization2015
- Normal Distributions Transform Occupancy Map fusion: Simultaneous mapping and tracking in large scale dynamic environments2013
- Normal distributions transform Monte-Carlo localization (NDT-MCL)2013
- Automatic appearance‐based loop detection from three‐dimensional laser data using the normal distributions transformJournal of Field Robotics, 2009
- Scan registration for autonomous mining vehicles using 3D‐NDTJournal of Field Robotics, 2007