Online Range Image-based Pole Extractor for Long-term LiDAR Localization in Urban Environments

TL;DR

This paper introduces a fast, online pole extraction method from range images for urban LiDAR localization, demonstrating high accuracy and robustness across diverse datasets without requiring GPU acceleration.

Contribution

A novel pole extraction approach directly from range images that is fast, accurate, and suitable for real-time localization in urban environments.

Findings

Outperforms state-of-the-art pole extraction methods

Operates online without GPU, suitable for real-time applications

Effective across various datasets, weather, and seasonal conditions

Abstract

Reliable and accurate localization is crucial for mobile autonomous systems. Pole-like objects, such as traffic signs, poles, lamps, etc., are ideal landmarks for localization in urban environments due to their local distinctiveness and long-term stability. In this paper, we present a novel, accurate, and fast pole extraction approach that runs online and has little computational demands such that this information can be used for a localization system. Our method performs all computations directly on range images generated from 3D LiDAR scans, which avoids processing 3D point cloud explicitly and enables fast pole extraction for each scan. We test the proposed pole extraction and localization approach on different datasets with different LiDAR scanners, weather conditions, routes, and seasonal changes. The experimental results show that our approach outperforms other state-of-the-art approaches, while running online without a GPU. Besides, we release our pole dataset to the public for evaluating the performance of pole extractor, as well as the implementation of our approach.