Image and Signal Processing Methods

Multimode image matching based on maximum similarity model and scale invariant feature transform for islands

[+] Author Affiliations
Ruirui Wang

Beijing Forestry University, College of Forestry, No. 35 Tsinghua East Road Haidian District, Beijing 100083, China

Wei Shi, Fenzhen Su

Chinese Academy of Sciences, Institute of Geographic Sciences and Natural Resources Research, State Key Laboratory of Resources and Environmental Information Systems, 11A, Datun Road, Chaoyang District, Beijing 100101, China

J. Appl. Remote Sens. 9(1), 095044 (Nov 09, 2015). doi:10.1117/1.JRS.9.095044
History: Received January 21, 2015; Accepted October 9, 2015
Text Size: A A A

Abstract.  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.

Figures in this Article
© 2015 Society of Photo-Optical Instrumentation Engineers

Citation

Ruirui Wang ; Wei Shi and Fenzhen Su
"Multimode image matching based on maximum similarity model and scale invariant feature transform for islands", J. Appl. Remote Sens. 9(1), 095044 (Nov 09, 2015). ; http://dx.doi.org/10.1117/1.JRS.9.095044


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.