空間—譜間字典的學(xué)習(xí)及基于字典的高光譜圖像的重構(gòu)
發(fā)布時(shí)間:2018-06-12 06:02
本文選題:高光譜圖像 + 字典學(xué)習(xí) ; 參考:《河北大學(xué)》2014年碩士論文
【摘要】:高光譜圖像的光譜具有顯著的結(jié)構(gòu)特征,如果高光譜圖像得到適當(dāng)?shù)谋碚骺梢詫?shí)現(xiàn)更高效的數(shù)據(jù)采集并且能夠提高數(shù)據(jù)的分析能力。因?yàn)榇蟛糠窒袼厮从车闹皇巧贁?shù)的幾種材料光譜反射曲線,因此我們認(rèn)為稀疏編碼模型與高光譜圖像數(shù)據(jù)是良好匹配的。稀疏模型認(rèn)為每個(gè)像素只是一個(gè)較大的字典中幾個(gè)元素的組合,并且這種方法在應(yīng)用中被證明很有效。 本文提出了一種新的空間-譜間字典的學(xué)習(xí)方法,并用這個(gè)字典進(jìn)行高光譜圖像的重構(gòu)。本文采用梯度下降法學(xué)習(xí)字典,并對(duì)梯度下降法做了簡(jiǎn)要的介紹。同時(shí),本文提出了空間-譜間字典的學(xué)習(xí)基本思路。首先,,初始化字典取隨機(jī)正值,固定字典利用梯度下降法計(jì)算稀疏系數(shù);其次,系數(shù)不變?cè)儆锰荻认陆捣ㄓ?xùn)練更新字典;最后,上述兩步交替進(jìn)行直到算法收斂。依據(jù)這種模型訓(xùn)練出來(lái)的字典更加符合高光譜圖像的特點(diǎn),并將訓(xùn)練出來(lái)的字典用于高光譜圖像的重構(gòu),通過(guò)比較峰值信噪比PSNR來(lái)確定圖像重構(gòu)效果的好壞,本文通過(guò)字典重構(gòu)的圖像的PSNR與原始圖像比較獲得了良好的重構(gòu)效果。
[Abstract]:The spectrum of hyperspectral image has significant structural features , and if the hyperspectral image is properly characterized , more efficient data acquisition can be realized and the analytical capability of data can be improved . Because most of the pixels reflect only a small number of spectral reflection curves of the material , we think that the sparse coding model is well matched with hyperspectral image data . The sparse model considers that each pixel is a combination of several elements in a larger dictionary , and this method is proved to be effective in application .
This paper presents a new learning method of space - spectrum dictionary , and uses this dictionary to reconstruct hyperspectral image . In this paper , the gradient descent method is used to study the dictionary , and the gradient descent method is introduced briefly . At the same time , this paper presents the basic idea of learning the space - spectrum dictionary . First , the initialization dictionary takes the random value , and the fixed dictionary calculates the sparse coefficient by gradient descent method .
secondly , training the updating dictionary by a gradient descent method ;
finally , the two steps are alternately carried out until the algorithm converges , the dictionary trained by the model is more consistent with the characteristics of hyperspectral images , and the trained dictionary is used for reconstruction of hyperspectral images , and the quality of the image reconstruction effect is determined by comparing the peak signal - to - noise ratio psnr , and a good reconstruction effect is obtained by comparing the psnr of the image reconstructed by the dictionary and the original image .
【學(xué)位授予單位】:河北大學(xué)
【學(xué)位級(jí)別】:碩士
【學(xué)位授予年份】:2014
【分類號(hào)】:TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前8條
1 粘永健;辛勤;湯毅;萬(wàn)建偉;;基于多波段預(yù)測(cè)的高光譜圖像分布式無(wú)損壓縮[J];光學(xué)精密工程;2012年04期
2 吳超;吳一全;;基于混沌粒子群優(yōu)化投影尋蹤的高光譜圖像目標(biāo)檢測(cè)[J];光學(xué)學(xué)報(bào);2011年12期
3 肖竹;王素玉;卓力;;成像光譜圖像壓縮技術(shù)研究的新進(jìn)展[J];測(cè)控技術(shù);2009年05期
4 張春梅;尹忠科;肖明霞;;基于冗余字典的信號(hào)超完備表示與稀疏分解[J];科學(xué)通報(bào);2006年06期
5 董超;趙慧潔;;關(guān)聯(lián)向量機(jī)在高光譜影像分類中的應(yīng)用[J];遙感學(xué)報(bào);2010年06期
6 吳一全;吳超;;基于小波和支持向量回歸的高光譜遙感圖像壓縮[J];宇航學(xué)報(bào);2011年03期
7 劉春紅,趙春暉,張凌雁;一種新的高光譜遙感圖像降維方法[J];中國(guó)圖象圖形學(xué)報(bào);2005年02期
8 練秋生;趙陽(yáng);;基于空間-光譜字典的不完備高光譜圖像重構(gòu)[J];儀器儀表學(xué)報(bào);2013年01期
本文編號(hào):2008632
本文鏈接:http://sikaile.net/guanlilunwen/gongchengguanli/2008632.html
最近更新
教材專著