|
|
A New RS Image Fusion Method Based on Feature |
WANG Wen-jun, QIN Qi-ming, CHEN Si-jin, FU Wei |
1.Laboratory of Remote Sensing and GIS,Peking University,Beijing100871,China;2.Communication and Electronic Department,Communication Engineering College, |
|
|
Abstract The image feature fusion is a kind of data fusion that is based on spectral structure and texturefeature of the objects. This paper proposed feature fusion after enhancing image edge with wavelet’smulti-resolution analysis to largely improve image' s definition and resolving power. In the fusion process,instead of using the conventional HIS-Wavelet fusion, directly introduced RGB-Wavelet transformationwhich decomposed RGB bands of the multi-spectral image and high-resolution image by waveletseparately, then used low frequent parts of the R, G, B bands and high frequent parts of the high-resolution image to do the image fusion, finally had new R, G, B bands as the new fusion image. In theway, not only improved definition and resolution of the multi-spectral image, but also retained the colorfeature of multi-spectral image which was important for multi-spectral fusion. At last validated theconclusion with an experiment. This method was based on wavelet multi-resolution analysis and RGB colorspace, so it didn' t generate any compute error of color space transform. Compared the fusion results of RGB-wavelet and HIS-wavelet methods, it could find that not only precision of visual estimation but alsoguide lines of quantitative analysis such as definition, space resolution had greater improvement.
|
Received: 09 November 2003
Published: 26 December 2011
|
|
〔1〕 江东,王珏,王建华,等.多源图像信息融合的理论与技术〔J〕.甘肃科学学报,2002,1:41~45.〔2〕 徐建华,王洪华.基于HIS变换和小波变换的遥感图像融合〔J〕.信息工程大学测绘学院,2002.9.〔3〕 Mallat S. A Theory for Multi-Resolution Signal Decomposi- tion: The Wavelet Representation〔J〕.IEEE Trans Patt,AnalMachine Intell, 1989,7:674~693.〔4〕 Martin. Wavelet and Filter Banks: Theory and Design〔J〕.IEEE Trans Signal Processing,1992,40:2207~2232. |
No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|