本文關(guān)鍵詞：基于BP神經(jīng)網(wǎng)絡(luò)的遙感影像分類研究　出處：《東華理工大學》2014年碩士論文　論文類型：學位論文

  更多相關(guān)文章： 遙感影像分類 改進型BP神經(jīng)網(wǎng)絡(luò) 遺傳算法 NDVI指數(shù) 紋理特征

【摘要】：遙感技術(shù)(Remote Sensing,簡稱RS)以其數(shù)據(jù)高時效、多綜合的特點,已經(jīng)成為地球觀測一個重要技術(shù)手段。根據(jù)遙感技術(shù)獲取的遙感影像具有多光譜、高分辨率、多時相的特點,通過對原始數(shù)據(jù)做進一步的處理,就能夠發(fā)現(xiàn)事物變化規(guī)律,從而有效預測其未來趨勢,因此遙感影像的研究越來越受到學者的關(guān)注,而遙感影像分類則一直是該領(lǐng)域的研究熱點。人工神經(jīng)網(wǎng)絡(luò)是模擬人腦功能的一種網(wǎng)絡(luò)結(jié)構(gòu),具有自適應(yīng)、自組織、自學習的能力,能夠?qū)崿F(xiàn)信息的分布式存儲、并行處理,因其本身是一個非線性系統(tǒng),適合于解決復雜的非線性問題,諸如遙感影像分類。BP神經(jīng)網(wǎng)絡(luò)是一種誤差反向傳播的神經(jīng)網(wǎng)絡(luò),它能夠?qū)W習誤差反饋到隱含層,改變初始網(wǎng)絡(luò)結(jié)構(gòu)的權(quán)值和閾值,從而達到預期的學習目標。實踐證明,BP神經(jīng)網(wǎng)絡(luò)能夠極大地提高影像分類精度。然而,BP神經(jīng)網(wǎng)絡(luò)在應(yīng)用過程中也存在一些問題:易限入局部極小值,網(wǎng)絡(luò)收斂速度慢,隱含層神經(jīng)元個數(shù)無法確定,無法妥善解決影像中存在的“同物異譜,同譜異物”問題。針對上述問題,本文以覆蓋江蘇江陰、靖江及其周邊的LANDSAT-7影像為實驗數(shù)據(jù),將遺傳算法與BP算法相結(jié)合,對BP神經(jīng)網(wǎng)絡(luò)的初始權(quán)值進行優(yōu)化,同時獲得隱含層最優(yōu)神經(jīng)元數(shù)目。為了解決影像中存在的“同物異譜,同譜異物”問題,將NDVI指數(shù)值作為影像特征,與影像的紋理特征、光譜信息相結(jié)合共同用于影像分類。最后采用改進后的BP神經(jīng)網(wǎng)絡(luò)對結(jié)合NDVI指數(shù)、紋理特征、光譜信息的數(shù)據(jù)進行分類,并將其結(jié)果與傳統(tǒng)方法的結(jié)果進行比較。實驗結(jié)果表明:改進后的BP神經(jīng)網(wǎng)絡(luò)的分類效果和精度有了明顯的提高。
[Abstract]:Remote Sensing (RS) has become an important technical means for earth observation because of its high aging and multi comprehensive data. According to the remote sensing image remote sensing images with high resolution, multi spectral and multi temporal characteristics, through further processing of the original data, we can found the changes of things, so as to predict its future trend, so the research of remote sensing image is more and more attention of scholars, and the remote sensing image classification is always a hotspot the field. Artificial neural network is a kind of network structure to simulate the human brain function, adaptive, self-organizing and self-learning ability, can realize distributed information storage, parallel processing, because of its itself is a nonlinear system, suitable for solving complex nonlinear problems, such as remote sensing image classification. BP neural network is an error back propagation neural network. It can feedback learning errors to the hidden layer and change the weights and thresholds of the initial network structure, so as to achieve the desired learning objectives. It has been proved that the BP neural network can greatly improve the accuracy of image classification. However, BP neural network has some problems in the application process: easy to limit into the local minimum, slow convergence rate, the number of hidden neurons can not be determined, unable to properly solve the image in the different spectrums of the same spectral problem. To solve the above problems, we take the LANDSAT-7 images covering Jiangsu Jiangyin, Jingjiang and its surrounding area as experimental data, combine genetic algorithm with BP algorithm, optimize the initial weights of BP neural network, and get the optimal number of neurons in hidden layer at the same time. In order to solve the image in the different spectrums of same spectrum, NDVI refers to the value as image features, texture features, image and spectral information together for image classification. Finally, the improved BP neural network is used to classify the data combined with NDVI index, texture feature and spectral information, and the results are compared with the results of traditional methods. The experimental results show that the classification effect and accuracy of the improved BP neural network have been greatly improved.
【學位授予單位】：東華理工大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：P237

【共引文獻】

相關(guān)博士學位論文 前1條

1 王鑫;基于高分辨率遙感影像的植被分類方法研究[D];北京林業(yè)大學;2015年

，

本文編號：1339163