SeqLPD: Sequence Matching Enhanced Loop-Closure Detection Based on Large-Scale Point Cloud Description for Self-Driving Vehicles

TL;DR

This paper introduces SeqLPD, a novel loop-closure detection method for self-driving vehicles that combines deep learning-based point cloud descriptors with a coarse-to-fine sequence matching strategy to improve accuracy and real-time performance.

Contribution

It presents a new deep neural network for global point cloud description and a sequence matching approach that enhances loop-closure detection in large-scale environments.

Findings

Improves loop-closure detection accuracy over existing deep-learning methods

Achieves real-time performance in self-driving vehicle scenarios

Validated effectiveness through experiments on a self-driving vehicle

Abstract

Place recognition and loop-closure detection are main challenges in the localization, mapping and navigation tasks of self-driving vehicles. In this paper, we solve the loop-closure detection problem by incorporating the deep-learning based point cloud description method and the coarse-to-fine sequence matching strategy. More specifically, we propose a deep neural network to extract a global descriptor from the original large-scale 3D point cloud, then based on which, a typical place analysis approach is presented to investigate the feature space distribution of the global descriptors and select several super keyframes. Finally, a coarse-to-fine strategy, which includes a super keyframe based coarse matching stage and a local sequence matching stage, is presented to ensure the loop-closure detection accuracy and real-time performance simultaneously. Thanks to the sequence matching operation, the proposed approach obtains an improvement against the existing deep-learning based methods. Experiment results on a self-driving vehicle validate the effectiveness of the proposed loop-closure detection algorithm.