Robust Edge-Direct Visual Odometry based on CNN edge detection and Shi-Tomasi corner optimization

TL;DR

This paper introduces a robust visual odometry method that combines CNN-based edge detection and corner optimization, utilizing a pyramid approach and Levenberg-Marquardt optimization to improve accuracy and robustness over existing methods.

Contribution

The paper presents a novel edge-direct visual odometry approach integrating CNN edge detection with Shi-Tomasi corner optimization and pyramid-based motion estimation.

Findings

Outperforms dense direct and Canny-based methods in robustness.

Achieves higher accuracy compared to existing VO systems.

Demonstrates improved performance on RGB-D TUM benchmark.

Abstract

In this paper, we propose a robust edge-direct visual odometry (VO) based on CNN edge detection and Shi-Tomasi corner optimization. Four layers of pyramids were extracted from the image in the proposed method to reduce the motion error between frames. This solution used CNN edge detection and Shi-Tomasi corner optimization to extract information from the image. Then, the pose estimation is performed using the Levenberg-Marquardt (LM) algorithm and updating the keyframes. Our method was compared with the dense direct method, the improved direct method of Canny edge detection, and ORB-SLAM2 system on the RGB-D TUM benchmark. The experimental results indicate that our method achieves better robustness and accuracy.