Share Email Print
cover

Proceedings Paper

An improved image matching algorithm based on SURF and Delaunay TIN
Author(s): Yuan-ming Cheng; Peng-gen Cheng; Xiao-yong Chen; Shou-zhu Zheng
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Image matching is one of the key technologies in the image processing. In order to increase its efficiency and precision, a new method for image matching which based on the improved SURF and Delaunay-TIN is proposed in this paper. Based on the original SURF algorithm, three constraint conditions, color invariant model, Delaunay-TIN, triangle similarity function and photography invariant are added into the original SURF model. With the proposed algorithm, the image color information is effectively retained and the erroneous matching rate of features is largely reduced. The experimental results shows that this proposed method has the characteristics of higher matching speed, uniform distribution of feature points to be matched, and higher correct matching rate than the original algorithm does.

Paper Details

Date Published: 9 December 2015
PDF: 9 pages
Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 980811 (9 December 2015); doi: 10.1117/12.2207665
Show Author Affiliations
Yuan-ming Cheng, East China Institute of Technology (China)
Nanchang Institute of Urban Planning and Survey (China)
Peng-gen Cheng, East China Institute of Technology (China)
Guangxi Key Lab. of Spatial Information and Geomatics (China)
Xiao-yong Chen, East China Institute of Technology (China)
Shou-zhu Zheng, East China Institute of Technology (China)


Published in SPIE Proceedings Vol. 9808:
International Conference on Intelligent Earth Observing and Applications 2015
Guoqing Zhou; Chuanli Kang, Editor(s)

© SPIE. Terms of Use
Back to Top