Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network

TL;DR

This paper introduces a stereo visual odometry method that leverages deep learning-based point and line feature matching with an attention graph neural network, enhancing robustness in adverse weather and lighting conditions.

Contribution

The paper proposes a novel feature-matching mechanism using an attention graph neural network for stereo visual odometry, improving performance in challenging environmental conditions.

Findings

Achieves more line feature matches than state-of-the-art algorithms.

Performs reliably under fog, rain, snow, and nighttime conditions.

Maintains consistent odometry accuracy in adverse environments.

Abstract

Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor scenes is a major challenge and still remains an open area of research. In this paper, we present a Stereo Visual Odometry (StereoVO) technique based on point and line features which uses a novel feature-matching mechanism based on an Attention Graph Neural Network that is designed to perform well even under adverse weather conditions such as fog, haze, rain, and snow, and dynamic lighting conditions such as nighttime illumination and glare scenarios. We perform experiments on multiple real and synthetic datasets to validate the ability of our method to perform StereoVO under low visibility weather and lighting conditions through robust point and line matches. The results demonstrate that our method achieves more line feature matches than state-of-the-art line matching algorithms, which when complemented with point feature matches perform consistently well in adverse weather and dynamic lighting conditions.