Pole-based Vehicle Localization with Vector Maps: A Camera-LiDAR Comparative Study

TL;DR

This paper compares pole-based vehicle localization methods using vector maps with camera and LiDAR sensors, demonstrating a real-time neural network approach for camera detection and highlighting its accuracy in open road scenarios.

Contribution

It introduces a real-time camera-based pole detection method using a lightweight neural network and provides a comparative evaluation of camera and LiDAR approaches for pole-based localization.

Findings

Vision-based pole detection achieves high accuracy in open roads.

Multi-camera integration enhances detection reliability.

The proposed neural network is efficient for real-time applications.

Abstract

For autonomous navigation, accurate localization with respect to a map is needed. In urban environments, infrastructure such as buildings or bridges cause major difficulties to Global Navigation Satellite Systems (GNSS) and, despite advances in inertial navigation, it is necessary to support them with other sources of exteroceptive information. In road environments, many common furniture such as traffic signs, traffic lights and street lights take the form of poles. By georeferencing these features in vector maps, they can be used within a localization filter that includes a detection pipeline and a data association method. Poles, having discriminative vertical structures, can be extracted from 3D geometric information using LiDAR sensors. Alternatively, deep neural networks can be employed to detect them from monocular cameras. The lack of depth information induces challenges in associating camera detections with map features. Yet, multi-camera integration provides a cost-efficient solution. This paper quantitatively evaluates the efficacy of these approaches in terms of localization. It introduces a real-time method for camera-based pole detection using a lightweight neural network trained on automatically annotated images. The proposed methods' efficiency is assessed on a challenging sequence with a vector map. The results highlight the high accuracy of the vision-based approach in open road conditions.