The Remote Sensing Image Matching Algorithm Based on the Normalized Cross-Correlation and SIFT
- PDF / 449,762 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 92 Downloads / 173 Views
SHORT NOTE
The Remote Sensing Image Matching Algorithm Based on the Normalized Cross-Correlation and SIFT Xingxing Shen & Wenxing Bao
Received: 14 June 2013 / Accepted: 3 September 2013 # Indian Society of Remote Sensing 2013
Abstract SIFT (scale invariant feature transform) is one of the most robust and widely used image matching algorithms based on local features. However, its computational complexity is high. In order to reduce the matching time, an improved feature matching algorithm is proposed in this paper under the premise of stable registration accuracy. This paper proposed a normalized crosscorrelation with SIFT combination of remote sensing image matching algorithm. The basic idea of the algorithm is performing the space geometry transformation of the input image with reference to the base image. Then the normalized cross-correlation captures the relevant part of the remote sensing images. By this way, we can reduce the matching range. So some unnecessary calculations are properly omitted. By utilizing the SIFT algorithm, we match the preprocessed remote sensing images, and get the registration points. This can shorten the matching time and improve the matching accuracy. Its robustness is increased correspondingly. The experimental results show that the proposed Normalized cross-correlation plus SIFT algorithm is more rapid than the standard SIFT algorithm while the performance is favorably compared to the standard SIFT algorithm when matching among structured scene images. The experiment results confirm the feasibility of our methods.
Keywords Normalized cross-correlation . SIFT . Remote sensing
X. Shen : W. Bao (*) School of Computer Science and Engineering, Beifang University of Nationalities, No.204 Wenchang, North-Street, Xixia District, Yinchuan, Ningxia, China 750021 e-mail: [email protected]
Introduction SIFT (Lowe 2004, 1999) feature matching algorithm is proposed by David G. Lowe in 2004 on the basis of summarizing the existing feature detection methods which based on invariant technology. It is invariant to image translation, scaling, rotation, and even affine transformation. The SIFT features are local image features, the features are invariant to rotation, scaling, and illumination changes, and partially stable to perspective changes, affine transformation, and noise. SIFT is a classic image matching algorithm. SIFT features can be used in large signature database for accurate matching. Based on SIFT characteristic operator matching method has been successfully applied to many areas. Although the SIFT algorithm having the above advantages,SIFT algorithm is a time consuming algorithm. And SIFT feature matching calculation capacity, efficiency is not high. In order to reduce the matching time and improve efficiency, an improved feature matching algorithm is proposed in this paper under the premise of stable registration accuracy. The main idea is the image which processed by space transform and NCC (Song 2011; Al-Qubaa et al. 2010) as SIFT input image. This method combines normalized cross-c
Data Loading...
