Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network
This addresses the problem of reliable visual odometry for autonomous systems in challenging environments like fog, rain, and nighttime, representing an incremental improvement with a novel matching mechanism.
The paper tackles the challenge of robust feature matching in texture-poor scenes for visual odometry by introducing a stereo visual odometry method using point and line features with an attention graph neural network, achieving more line feature matches than state-of-the-art algorithms and consistent performance in adverse weather and lighting conditions.
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.