QQ客服 官方微博 反馈留言

	Multimode image matching based on maximum similarity model and scale invariant feature transform for islands
	Wang R. R.; Shi, W.; Su, F. Z.
	2015
关键词	image matching Huangyan Island scale invariant feature transform maximum similarity model statistical circle registration
英文摘要	Different from the images of villages or towns where many homologous features can be extracted easily, the extraction of homologous features from multimode images located of sea islands is more difficult because the types of objects on sea islands are hard to recognize. When applying scale invariant feature transform (SIFT) to the image matching of sea islands, only sparsely matched couples with an uneven distribution are obtained. To resolve this problem, a new feature point matching method that combines a maximum similarity model and scale invariant feature transform (MS-SIFT) is proposed. This method can solve the primary difficulty of matching multimode images, which is to extract the massive feature points that are invariant to differences in spectrum, scale, and view angles between multimode images, and successfully obtain many precise matched couples of images located in areas with less remarkable features, especially for matching images of sea islands with less features. The application of the proposed algorithm shows that a large number of accurately matched couples could be identified. Additionally, the matched accuracy, space uniformity of the matched couples, and the running time computed based on the MS-SIFT and the traditional SIFT are analyzed and compared, which further demonstrate the effectiveness of the proposed algorithm. (C) 2015 Society of Photo-Optical Instrumentation Engineers (SPIE)
出处	Journal of Applied Remote Sensing
卷	9
语种	英语
ISSN号	1931-3195
DOI标识	10.1117/1.jrs.9.095044
内容类型	SCI/SSCI论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/43490]
专题	地理科学与资源研究所_历年回溯文献
推荐引用方式 GB/T 7714	Wang R. R.,Shi, W.,Su, F. Z.. Multimode image matching based on maximum similarity model and scale invariant feature transform for islands. 2015.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。