本文選題：高光譜圖像分類 + 復(fù)合核��； 參考：《湖北大學(xué)》2014年碩士論文

【摘要】：高光譜遙感是將成像技術(shù)和細(xì)分光譜技術(shù)結(jié)合在一起的多維信息獲取技術(shù),伴隨著成像光譜技術(shù)的迅速發(fā)展,高光譜圖像分類識(shí)別技術(shù)日漸完善,在各種應(yīng)用領(lǐng)域得到了廣泛運(yùn)用和發(fā)展.傳統(tǒng)的常用分類算法最大似然估計(jì)和神經(jīng)網(wǎng)絡(luò)在使用維數(shù)高、波段之間相關(guān)性大的高光譜數(shù)據(jù)時(shí)則會(huì)遭遇維數(shù)災(zāi)難現(xiàn)象.支持向量機(jī)是解決維數(shù)災(zāi)難問(wèn)題的核方法之一,與支持向量機(jī)相對(duì)應(yīng)的相關(guān)向量機(jī),卻只需要更少的相關(guān)向量和更快的測(cè)試時(shí)間,就可得到與支持向量機(jī)相接近的準(zhǔn)確率,相關(guān)向量機(jī)用于高光譜圖像分類,有著自身的優(yōu)勢(shì)和不足. 作為另一種核方法的相關(guān)向量機(jī),很好的解決了維數(shù)災(zāi)難問(wèn)題.基于相關(guān)向量機(jī)分類準(zhǔn)確率不高的事實(shí),考慮到高光譜數(shù)據(jù)本身具有空間信息等結(jié)構(gòu)特點(diǎn),為了彌補(bǔ)這一不足,本文以相關(guān)向量機(jī)為基本模型展開(kāi)研究,將高光譜圖像的空間信息與光譜信息融合在一起,并提出了一種新的基于復(fù)合核的相關(guān)向量機(jī)高光譜圖像分類算法.本文主要研究工作如下： (1)將相關(guān)向量機(jī)理論應(yīng)用到高光譜分類圖像中,提出了改進(jìn)型相關(guān)向量機(jī)分類算法,在真實(shí)的高光譜數(shù)據(jù)上進(jìn)行模擬實(shí)驗(yàn),并與傳統(tǒng)的支持向量機(jī)算法進(jìn)行較為詳細(xì)的比較. (2)提出了基于復(fù)合核的相關(guān)向量機(jī)高光譜圖像分類算法.該算法使用復(fù)合核,融合了空間特征與譜信息,既顧及到起分類主作用的譜特征,又利用了高光譜數(shù)據(jù)的空間差異性.考慮到權(quán)和核中譜信息和空間信息兩者之間所占比值的不同,繼而提出了廣義的復(fù)合核,避免了平衡參數(shù)的調(diào)節(jié),同時(shí)探討了不同窗口大小對(duì)各類分類器的分類精度的影響,從而保證了實(shí)驗(yàn)的可靠性和高效性. (3)本文提出的基于復(fù)合核的辦法能較好利用高光譜圖像數(shù)據(jù)的空間信息,在真實(shí)的高光譜數(shù)據(jù)實(shí)驗(yàn)上也驗(yàn)證了所提出的算法的有效性.
[Abstract]:Hyperspectral remote sensing is a multi - dimensional information acquisition technology combining imaging technology with subdivision spectrum technology . With the rapid development of imaging spectrum technology , high spectral image classification and recognition technology has been widely used and developed . Support vector machine is one of the kernel methods to solve the problem of dimension disaster . Support vector machine is one of the kernel methods to solve the problem of dimension disaster .

Based on the fact that the classification accuracy of the correlation vector machine is not high , the spatial information and the spectral information of the hyperspectral image are fused together in consideration of the fact that the high spectral data itself has spatial information and so on , and a new high spectral image classification algorithm based on the composite core is proposed . The main research work is as follows :

( 1 ) The correlation vector machine theory is applied to hyperspectral classification image , and the improved correlation vector machine classification algorithm is proposed , and the simulation experiment is carried out on the real hyperspectral data , and compared with the traditional support vector machine algorithm .

( 2 ) The high spectral image classification algorithm based on the complex kernel is proposed . The algorithm uses the complex kernel , combines the space feature and the spectral information , takes into account the spectral characteristics of the main function of the classification , and uses the spatial difference of the hyperspectral data . Considering the difference between the spectral information and the spatial information in the kernel , the generalized composite core is proposed , the influence of different window sizes on the classification accuracy of various classifiers is discussed , and the reliability and efficiency of the experiment are ensured .

( 3 ) The method based on the complex kernel presented in this paper can better utilize the spatial information of hyperspectral image data , and verify the effectiveness of proposed algorithm in real high spectral data experiment .
【學(xué)位授予單位】：湖北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蘇宗n，

本文編號(hào)：1940295