A Remote Sensing Image Fusion Algorithm Based on the Second Generation Curvelet Transform and DS Evidence Theory
- PDF / 390,064 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 52 Downloads / 175 Views
SHORT NOTE
A Remote Sensing Image Fusion Algorithm Based on the Second Generation Curvelet Transform and DS Evidence Theory Chunxue Huang & Wenxing Bao
Received: 23 May 2013 / Accepted: 16 December 2013 # Indian Society of Remote Sensing 2014
Abstract A new method of remote sensing image fusion is proposed based on the second generation Curvelet transform and Dempster-Shafer (DS) evidence theory. In this paper, the remote sensing images are decomposed by the Curvelet transform to get the coefficients and optimize the high coefficients with DS evidence theory. Firstly, the high resolution and multispectral remote sensing images are decomposed by the Curvelet transform to get the Curvelet transform coefficients of all layers (Coarse, Detail and Fine scale layer). Secondly, the Coarse scale layer is used the maximum fusion rule. The Detail scale layer is used by the weighted average fusion rule. The Fine scale layer is optimized by the DS evidence theory. Get the three features of the Fine scale layer coefficients. The three features are the variance, information entropy and energy. Use the features to be some parameters belief function and the plausibility function. Then compose the mass function and get new fusion coefficients. Finally, the fused image is obtained by the inverse Curvelet transform. The experimental results show that the new algorithm can more effectively than wavelet and other traditional fusion algorithms such as HIS, brovey in the remote sensing image fusion. Keywords The second generation Curvelet transform . Remote sensing image fusion . DS evidence theory
Introduction
the image processing requirements are also increasing. However, a variety of different methods of image processing are endless, and have great impact for the different fields of application, such as remote sensing, medical, criminal investigation. The purpose of remote sensing image fusion is to obtain the fusion image with high spectral resolution and high spatial resolution at the same time, and improve the capabilities of analysis and extraction of image information, and solve the lake of a single source of information content of remote sensing image (Wei and Wenxing 2012). In this paper, a new method of remote sensing image fusion is proposed based on the second generation Curvelet transform and the DS evidence theory. Curvelet transform is a new multi-scale transform developed on the basis of the wavelet transform. Its structural elements, including the scale and location parameters, have the orientation parameters that wavelet transform doesn’t have. Curvelet transform has the better characteristics of orientation (Yan and Licheng 2007). In the reference (Yao et al. 2012), the medical fusion images were decomposed by wavelet with multi-feature based on evidential theory. Get the coefficients and do with DS evidence theory. In the reference (Zhao 2012), the remote sensing image could get the better effects, but the light distortions degree was relatively poor. DS evidence theory was used with many algorithms, such as wav
Data Loading...
