A Texture-Based Feature Point Detection and Matching Method

This paper presents a method for detecting feature points from an image and locating their matching correspondence points across images. The proposed method leverages a novel rapid LBP (Local Binary Pattern) feature point detection to filter out texture-less feature points from SURF (Speeded Up Robust Features). The detected feature points, also known as Non-Uniform SURF feature points (NUS), are used to match corresponding feature points from other frame images to reliably locate positions of moving objects. The proposed method consists of two processing modules: Feature Point Extraction (FPE) and Feature Point Mapping (FPM). First, FPE extracts salient feature points with Feature Transform and Feature Point Detection. FPM is then applied to generate motion vectors of each feature point with Feature Descriptor and Feature Point Matching. Experiments are conducted on both artificial template patterns and real scenes captured from moving camera at different speed settings. Experiment results show that the proposed method outperforms the SURF method in detecting feature points and locating their corresponding points from videos.

並列關鍵字

Block matching ； feature point detection ； motion vector detection

國際替代計量

全文下載

主題瀏覽