本文選題：k-NN + 地統(tǒng)計(jì)模型�。� 參考：《南京大學(xué)》2013年碩士論文

【摘要】：隨著衛(wèi)星技術(shù)的發(fā)展,遙感影像的分辨率和數(shù)據(jù)量正在急劇增長(zhǎng),對(duì)遙感影像的處理技術(shù)提出了更高的要求。近幾十年來越來越多的研究人員投入到遙感分類方法的研究,使得分類精度不斷提高,應(yīng)用領(lǐng)域日益廣泛。特別是地統(tǒng)計(jì)方法的引入,使得不少研究人員開始注意到地物空間關(guān)系對(duì)遙感影像分類的影響。k-NN方法是常用的最近鄰分類器,易于與地統(tǒng)計(jì)模型相結(jié)合,將地物空間關(guān)系特征引入該分類器可提高分類精度。與此同時(shí),許多領(lǐng)域?qū)Ａ窟b感數(shù)據(jù)處理的時(shí)效性也提出了更高要求,高效并行化遙感影像處理是解決這一問題的有效途徑。因此,開發(fā)高精度的并行遙感分類器是遙感研究領(lǐng)域的一個(gè)重要發(fā)展方向。本文根據(jù)地理學(xué)第一定律和并行計(jì)算思想,提出了gwk-NN并行遙感分類器。具體而言,在常用的傳統(tǒng)k-NN分類器的基礎(chǔ)上結(jié)合地統(tǒng)計(jì)模型,建立地理加權(quán)的gwk-NN分類器,并采用數(shù)據(jù)并行、任務(wù)并行和雙重并行等三種模式,從算法和數(shù)據(jù)兩方面對(duì)分類器進(jìn)行了并行化。其中,數(shù)據(jù)并行采用對(duì)等式,任務(wù)并行采用主從式,雙重并行則混合使用了對(duì)等式與主從式并行方式。在此基礎(chǔ)上,以SPOT 5遙感影像作為實(shí)驗(yàn)數(shù)據(jù),選擇地物類別典型、空間連續(xù)性好的區(qū)域進(jìn)行試驗(yàn),對(duì)gwk-NN并行遙感分類器的分類精度和性能進(jìn)行了測(cè)試。結(jié)果表明：(1)gwk-NN分類器優(yōu)于k-NN、最大似然法(ML)、神經(jīng)網(wǎng)絡(luò)(NN)和支持向量機(jī)(SVM)等傳統(tǒng)分類器,分類精度得到顯著提高,噪聲明顯減少甚至消失,而且方法同樣簡(jiǎn)單、易用；(2)gwk-NN并行分類器在雙重并行模式下性能最好,實(shí)用性明顯增強(qiáng)。在該模式單機(jī)環(huán)境下,分類器的加速比最大達(dá)到了6.59,并行效率為82.4%,明顯優(yōu)于數(shù)據(jù)并行和任務(wù)并行模式下的分類器性能。綜上所述,本文在以下兩方面有所創(chuàng)新：(1)將不同的地統(tǒng)計(jì)模型與k-NN分類器結(jié)合得到新型gwk-NN分類器,明顯改善了傳統(tǒng)k-NN分類器的分類精度；(2)將并行計(jì)算引入遙感影像分類,對(duì)gwk-NN分類器進(jìn)行并行化改進(jìn),提高了gwk-NN分類器的分類性能。
[Abstract]:With the development of satellite technology, the resolution and data volume of remote sensing image are increasing rapidly. In recent decades, more and more researchers have devoted themselves to the research of remote sensing classification methods, which makes the classification accuracy improve and the application fields become more and more extensive. Especially with the introduction of geostatistical methods, many researchers have begun to notice the influence of spatial relationship of ground objects on classification of remote sensing images. The k-NN method is a commonly used nearest neighbor classifier and is easy to be combined with geostatistical models. The classification accuracy can be improved by introducing the spatial relation features of ground objects into the classifier. At the same time, many fields also put forward higher requirements for the timeliness of massive remote sensing data processing. Efficient parallel remote sensing image processing is an effective way to solve this problem. Therefore, the development of high precision parallel remote sensing classifier is an important development direction in remote sensing research field. Based on the first law of geography and the idea of parallel computing, a parallel remote sensing classifier of gwk-NN is presented in this paper. In particular, based on the traditional k-NN classifier, a geo-weighted gwk-NN classifier is established based on the geostatistical model, which adopts three models: data parallelism, task parallelism and double parallelism. The classifier is parallelized from algorithm and data. Among them, data parallelism is peer-to-peer, task parallelism is master-slave, and dual parallelism is a mixture of peer-to-peer and master-slave parallelism. On this basis, the spot 5 remote sensing image is used as experimental data to test the classification accuracy and performance of the gwk-NN parallel remote sensing classifier. The results show that: (1) gwk-NN classifier is superior to k-NN, maximum likelihood method (ML), neural network (NN), support vector machine (SVM) and other traditional classifiers, the classification accuracy is significantly improved, the noise is obviously reduced or even disappeared, and the method is as simple and easy to use; (2) the gwk-NN parallel classifier has the best performance in the dual parallel mode, and its practicability is obviously enhanced. The speedup ratio of the classifier is 6.59 and the parallel efficiency is 82.4, which is superior to the performance of the classifier in data parallel mode and task parallel mode. To sum up, this paper has some innovations in the following two aspects: (1) combining different geostatistical models with k-NN classifier, a new type of gwk-NN classifier is obtained, which obviously improves the classification accuracy of the traditional k-NN classifier; (2) parallel computing is introduced into remote sensing image classification. The parallel improvement of gwk-NN classifier improves the classification performance of gwk-NN classifier.
【學(xué)位授予單位】：南京大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP751;P237

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 胡山鷹;劉曉惠;金涌;;資源型城市可持續(xù)發(fā)展的思考[J];國(guó)土與自然資源研究;2011年03期

2 喬程;沈占鋒;吳寧;胡曉東;駱劍承;;空間鄰接支持下的遙感影像分類[J];遙感學(xué)報(bào);2011年01期

3 馬民濤;孫磊;韓松;張雁雁;王江萍;張菁;;空間統(tǒng)計(jì)分析集成技術(shù)及其在區(qū)域環(huán)境中的應(yīng)用[J];北京工業(yè)大學(xué)學(xué)報(bào);2010年04期

4 郭懷成;周豐;刀，

本文編號(hào)：2069144