AirVO: An Illumination-Robust Point-Line Visual Odometry

TL;DR

AirVO is a real-time, illumination-robust visual odometry system that combines learning-based corner detection with line feature matching, outperforming existing methods under varying lighting conditions.

Contribution

The paper introduces a novel VO system integrating CNN and GNN for robust feature detection and matching, optimized for real-time performance on low-power devices.

Findings

Outperforms state-of-the-art VO systems in accuracy and robustness

Operates in real-time on embedded platforms

Effective under diverse illumination conditions

Abstract

This paper proposes an illumination-robust visual odometry (VO) system that incorporates both accelerated learning-based corner point algorithms and an extended line feature algorithm. To be robust to dynamic illumination, the proposed system employs the convolutional neural network (CNN) and graph neural network (GNN) to detect and match reliable and informative corner points. Then point feature matching results and the distribution of point and line features are utilized to match and triangulate lines. By accelerating CNN and GNN parts and optimizing the pipeline, the proposed system is able to run in real-time on low-power embedded platforms. The proposed VO was evaluated on several datasets with varying illumination conditions, and the results show that it outperforms other state-of-the-art VO systems in terms of accuracy and robustness. The open-source nature of the proposed system allows for easy implementation and customization by the research community, enabling further development and improvement of VO for various applications.