Research Article
Image Matching Algorithm Based on Improved ORB Feature Extraction
3 downloads
@INPROCEEDINGS{10.1007/978-3-030-62483-5_21, author={Yang Qingjiang and Shan Chuang}, title={Image Matching Algorithm Based on Improved ORB Feature Extraction}, proceedings={Green Energy and Networking. 7th EAI International Conference, GreeNets 2020, Harbin, China, June 27-28, 2020, Proceedings}, proceedings_a={GREENETS}, year={2020}, month={11}, keywords={Illumination Illumination homogenization Feature extraction Dynamic local threshold}, doi={10.1007/978-3-030-62483-5_21} }- Yang Qingjiang
Shan Chuang
Year: 2020
Image Matching Algorithm Based on Improved ORB Feature Extraction
GREENETS
Springer
DOI: 10.1007/978-3-030-62483-5_21
Abstract
Ambient illumination is an important factor affecting the high mismatching rate of single threshold image matching algorithm. Therefore, this paper proposes a local dynamic threshold extraction algorithm. This algorithm needs to perform light homogenization processing in the image preprocessing stage and calculate the appropriate threshold of each pixel for feature point judgment during feature extraction, which can effectively alleviate the problem of missing extraction and multiple extraction during feature extraction of a single threshold.
Copyright © 2020–2025 ICST
