LiDAR Iris for Loop-Closure Detection

TL;DR

This paper introduces LiDAR Iris, a novel global descriptor for LiDAR point clouds that enables fast, pose-invariant loop-closure detection using binary signatures and Hamming distance, validated on multiple road sequences.

Contribution

The paper presents a new LiDAR Iris descriptor that improves loop-closure detection speed and accuracy, with a binary signature approach and Fourier transform-based invariance.

Findings

Achieves pose-invariant loop-closure detection using the Fourier transform.

Demonstrates excellent performance on five road-scene sequences.

Provides a fast, accurate method suitable for real-time applications.

Abstract

In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection. A binary signature image can be obtained for each point cloud after several LoG-Gabor filtering and thresholding operations on the LiDAR-Iris image representation. Given two point clouds, their similarities can be calculated as the Hamming distance of two corresponding binary signature images extracted from the two point clouds, respectively. Our LiDAR-Iris method can achieve a pose-invariant loop-closure detection at a descriptor level with the Fourier transform of the LiDAR-Iris representation if assuming a 3D (x,y,yaw) pose space, although our method can generally be applied to a 6D pose space by re-aligning point clouds with an additional IMU sensor. Experimental results on five road-scene sequences demonstrate its excellent performance in loop-closure detection.