Comparison of camera-based and 3D LiDAR-based loop closures across weather conditions

TL;DR

This paper evaluates camera, LiDAR, and combined loop closure methods under various weather conditions using the USyd dataset, highlighting the benefits of multi-sensory approaches for robust autonomous navigation.

Contribution

It provides a comparative analysis of camera and LiDAR-based loop closures, demonstrating the effectiveness of LiDAR supplementation in adverse weather conditions.

Findings

LiDAR-based loop closure improves performance in bad weather.

Multi-sensory (camera + LiDAR) approaches outperform single sensors.

A 16-line LiDAR can effectively supplement camera data for loop closure.

Abstract

Loop closure based on camera images provides excellent results on benchmarking datasets, but might struggle in real-world adverse weather conditions like direct sun, rain, fog, or just darkness at night. In automotive applications, the sensory setups include 3D LiDARs that provide information complementary to cameras. The presented article focuses on the evaluation of camera-based, LiDAR-based, and joint camera-LiDAR-based loop closures applying a similar processing pipeline consisting of a neural network under varying weather conditions using the newly available USyd dataset. The experiments performed on the same trajectories in diverse weather conditions over 50 weeks prove that a 16-line 3D LiDAR can be used to supplement image-based loop closure to increase loop closure performance. This proves that there is a need for more research into loop closures performed with multi-sensory setups.