A Feature Matching Method Based on Multi-Level Refinement Strategy

TL;DR

This paper introduces KTGP-ORB, a multi-level feature matching method that improves accuracy in visual SLAM by combining local appearance similarity, motion constraints, and global information, reducing errors significantly.

Contribution

The paper presents a novel multi-level refinement strategy for feature matching, integrating GMS and PROSAC algorithms to enhance matching precision in challenging conditions.

Findings

Reduces matching error by 29.92% on average in complex scenes.

Improves robustness against illumination variations and blur.

Demonstrates superior performance over traditional ORB matching.

Abstract

Feature matching is a fundamental and crucial process in visual SLAM, and precision has always been a challenging issue in feature matching. In this paper, based on a multi-level fine matching strategy, we propose a new feature matching method called KTGP-ORB. This method utilizes the similarity of local appearance in the Hamming space generated by feature descriptors to establish initial correspondences. It combines the constraint of local image motion smoothness, uses the GMS algorithm to enhance the accuracy of initial matches, and finally employs the PROSAC algorithm to optimize matches, achieving precise matching based on global grayscale information in Euclidean space. Experimental results demonstrate that the KTGP-ORB method reduces the error by an average of 29.92% compared to the ORB algorithm in complex scenes with illumination variations and blur.