NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation

TL;DR

This paper introduces NDT-Transformer, a novel method for large-scale 3D point cloud place recognition that combines probabilistic NDT representations with a transformer network to improve accuracy in GPS-challenged environments.

Contribution

The paper presents a new approach integrating NDT representations with a transformer network for enhanced 3D place recognition in large-scale environments.

Findings

Achieves 7.52% higher top 1 recall than state-of-the-art methods.

Improves top 1% recall by 2.73% on Oxford Robotcar benchmark.

Enriches global descriptors with geometrical and contextual information.

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 realtime 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.