Work

Improved Feature Extracting and Matching Algorithm Based on FAST and Local Binary Pattern

Year: 2024

Type: conference-paper

Abstract: This study introduces an enhanced version of the FAST algorithm aimed at achieving a uniform distribution of feature points. We also developed a feature descriptor based on local binary patterns (LBP), which provides rotation invariance and robust anti-noise capabilities. Furthermore, we have designed specific feature-matching algorithms tailored for these descriptors and created methods to identify and eliminate mismatched features. Finally, we thoroughly assess the algorithm's real-time performance and locating accuracy using a publicly available dataset. The experimental results demonstrate that our algorithm performs well in localization accuracy, with a running time that is approximately 10% of that of the SURF algorithm and just 1% of that required by the SIFT algorithm.

Source: International Conference on Computer, Internet of Things and Smart City (CIoTSC)

DOI: 10.1145/3731867.3731877

Authors: Zhen Zhang, Zhen Zhang, Jianfang Zhu, Zhaoqi Zhang, Zhaoqi Zhang, Jinzhan Wei, Jiyue Wang, Hongkuang Tang

Institutions: Guilin University of Aerospace Technology, Beibu Gulf University

Language: English

Topic: Advanced Image and Video Retrieval Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Natural Science Foundation of Guangxi Province

OpenAlex ID: W4411022627

FWCI: 0.211

Cites: 13

Cited by: 1

Related to: 10