基于半監(jiān)督局部保持投影的高光譜遙感影像分類方法研究
發(fā)布時間：2018-08-03 14:46
【摘要】：高光譜遙感影像具有所含光譜信息量大、相關性強的大數(shù)據(jù)量等特點，若用傳統(tǒng)分類算法對其進行分類易產生“維數(shù)災難”，因此對高維數(shù)據(jù)進行降維處理則顯得尤為重要。在諸多降維算法中，如主成分分析(PCA)算法、線性判別分析(LDA)算法等，它們或是不能有效利用數(shù)據(jù)中的類別信息，或是對數(shù)據(jù)的類別信息要求嚴格。針對這些問題，論文提出一種半監(jiān)督局部保持投影(SSLPP)算法。 論文首先對高光譜圖像及其自身特點作簡單介紹，并結合監(jiān)督學習與非監(jiān)督學習對高維數(shù)據(jù)的特征提取方法進行總結和分析，提出SSLPP算法；其次從SSLPP算法的原理、算法流程等方面，對算法進行詳細介紹；為驗證SSLPP算法的有效性，與目前幾種主流特征提取算法進行對比性實驗，如主成分分析(PCA)算法、局部保持投影(LPP)算法、監(jiān)督局部保持投(SLPP)算法。實驗中對兩種實際情況下的高光譜遙感圖像數(shù)據(jù)進行分類實驗，，首先用各種算法對原數(shù)據(jù)集進行降維處理，然后使用K近鄰分類器對低維數(shù)據(jù)進行判類識別，計算出各個算法的總體分類精度，由此實驗結果對SSLPP算法的有效性進行驗證；最后為了探究SSLPP算法與各種分類器的融合性，分別用三種分類器與之結合對四種遙感圖像進行地物分類實驗，結果表明在該算法下各分類器均獲得較高識別率，由此驗證SSLPP算法具有較好的融合性。 經過實驗分析，論文所提SSLPP算法相比較于其他特征提取算法具有以下幾點優(yōu)勢：①SSLPP算法相對于非監(jiān)督降維算法，它充分利用了數(shù)據(jù)中的類別信息，使高維數(shù)據(jù)經過低維映射后具有較好的可分性；②SSLPP算法相對于監(jiān)督降維算法，其不僅利用了數(shù)據(jù)中的標記樣本并同時充分利用大量的未標記樣本，使得在進行低維投影時更好的把握原始數(shù)據(jù)的整體性；③在對高光譜數(shù)據(jù)進行分類處理，SSLPP保證較高分類精度的同時，又避免了對原始數(shù)據(jù)的全類別標定工作，從而很好的提高數(shù)據(jù)計算處理效率。 綜上所述，論文主要研究了高光譜遙感圖像基于半監(jiān)督學習的特征提取與分類方法，提出一種半監(jiān)督數(shù)據(jù)特征提取算法，通過對幾種實際高光譜遙感圖像的分類識別實驗證明了論文算法的有效性。
[Abstract]:Hyperspectral remote sensing images are characterized by large amount of spectral information and large amount of data with strong correlation. If the traditional classification algorithm is used to classify hyperspectral remote sensing images, it is easy to produce "dimensionality disaster", so it is very important to reduce the dimension of high-dimensional data. In many dimensionality reduction algorithms, such as principal component analysis (PCA) algorithm, linear discriminant analysis (LDA) algorithm and so on, they either can not effectively use the category information in the data or require strictly the data category information. In order to solve these problems, this paper presents a semi-supervision department preserving projection (SSLPP) algorithm. Firstly, the hyperspectral image and its own characteristics are briefly introduced, and the feature extraction methods of high-dimensional data are summarized and analyzed by combining supervised learning and unsupervised learning, and then the SSLPP algorithm is proposed, and then the principle of SSLPP algorithm is introduced. In order to verify the effectiveness of the SSLPP algorithm, a comparative experiment is carried out with several popular feature extraction algorithms, such as principal component analysis (PCA) (PCA) algorithm, local preserving projection (LPP) algorithm, and so on. The Supervisory Department maintains the (SLPP) algorithm. In the experiment, two kinds of hyperspectral remote sensing image data are classified. Firstly, the original data set is reduced by various algorithms, and then the low-dimensional data is identified by K-nearest neighbor classifier. The overall classification accuracy of each algorithm is calculated, and the validity of SSLPP algorithm is verified by the experimental results. Finally, in order to explore the fusion of SSLPP algorithm with various classifiers, Three classifiers are used to classify the ground objects of four remote sensing images respectively. The results show that each classifier has a high recognition rate under this algorithm, which verifies that the SSLPP algorithm has a better fusion performance. After experimental analysis, compared with other feature extraction algorithms, the proposed SSLPP algorithm has the following advantages over the unsupervised dimensionality reduction algorithm, which makes full use of the class information in the data. Compared with the supervised dimensionality reduction algorithm, the high-dimensional data has good separability after low-dimensional mapping. It not only makes use of the labeled samples in the data, but also makes full use of a large number of unlabeled samples at the same time. In order to better grasp the integrity of the original data in the low-dimensional projection, the classification of the hyperspectral data can be processed by SSLPP to ensure a higher classification accuracy, and at the same time, the whole classification of the original data can be avoided. In order to improve the efficiency of data calculation and processing. To sum up, this paper mainly studies the feature extraction and classification method of hyperspectral remote sensing image based on semi-supervised learning, and proposes a semi-supervised data feature extraction algorithm. The effectiveness of the algorithm is proved by the classification and recognition experiments of several real hyperspectral remote sensing images.
【學位授予單位】：重慶大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：TP751
本文編號：2162081
[Abstract]:Hyperspectral remote sensing images are characterized by large amount of spectral information and large amount of data with strong correlation. If the traditional classification algorithm is used to classify hyperspectral remote sensing images, it is easy to produce "dimensionality disaster", so it is very important to reduce the dimension of high-dimensional data. In many dimensionality reduction algorithms, such as principal component analysis (PCA) algorithm, linear discriminant analysis (LDA) algorithm and so on, they either can not effectively use the category information in the data or require strictly the data category information. In order to solve these problems, this paper presents a semi-supervision department preserving projection (SSLPP) algorithm. Firstly, the hyperspectral image and its own characteristics are briefly introduced, and the feature extraction methods of high-dimensional data are summarized and analyzed by combining supervised learning and unsupervised learning, and then the SSLPP algorithm is proposed, and then the principle of SSLPP algorithm is introduced. In order to verify the effectiveness of the SSLPP algorithm, a comparative experiment is carried out with several popular feature extraction algorithms, such as principal component analysis (PCA) (PCA) algorithm, local preserving projection (LPP) algorithm, and so on. The Supervisory Department maintains the (SLPP) algorithm. In the experiment, two kinds of hyperspectral remote sensing image data are classified. Firstly, the original data set is reduced by various algorithms, and then the low-dimensional data is identified by K-nearest neighbor classifier. The overall classification accuracy of each algorithm is calculated, and the validity of SSLPP algorithm is verified by the experimental results. Finally, in order to explore the fusion of SSLPP algorithm with various classifiers, Three classifiers are used to classify the ground objects of four remote sensing images respectively. The results show that each classifier has a high recognition rate under this algorithm, which verifies that the SSLPP algorithm has a better fusion performance. After experimental analysis, compared with other feature extraction algorithms, the proposed SSLPP algorithm has the following advantages over the unsupervised dimensionality reduction algorithm, which makes full use of the class information in the data. Compared with the supervised dimensionality reduction algorithm, the high-dimensional data has good separability after low-dimensional mapping. It not only makes use of the labeled samples in the data, but also makes full use of a large number of unlabeled samples at the same time. In order to better grasp the integrity of the original data in the low-dimensional projection, the classification of the hyperspectral data can be processed by SSLPP to ensure a higher classification accuracy, and at the same time, the whole classification of the original data can be avoided. In order to improve the efficiency of data calculation and processing. To sum up, this paper mainly studies the feature extraction and classification method of hyperspectral remote sensing image based on semi-supervised learning, and proposes a semi-supervised data feature extraction algorithm. The effectiveness of the algorithm is proved by the classification and recognition experiments of several real hyperspectral remote sensing images.
【學位授予單位】：重慶大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：TP751
【參考文獻】
相關期刊論文 前7條
1 王立志;黃鴻;馮海亮;;基于SSMFA與kNNS算法的高光譜遙感影像分類[J];電子學報;2012年04期
2 黃鴻;李見為;馮海亮;;基于有監(jiān)督核局部線性嵌入的面部表情識別[J];光學精密工程;2008年08期
3 譚琨;杜培軍;;基于支持向量機的高光譜遙感圖像分類[J];紅外與毫米波學報;2008年02期
4 袁國強;肖倩;劉強;;帶有最小風險準則的兩階段模糊運輸模型[J];計算機工程與應用;2011年35期
5 申中華;潘永惠;王士同;;有監(jiān)督的局部保留投影降維算法[J];模式識別與人工智能;2008年02期
6 任廣波;張杰;馬毅;鄭榮兒;;生成模型學習的遙感影像半監(jiān)督分類[J];遙感學報;2010年06期
7 趙慧潔;葛文謙;李旭東;;最小誤差準則與脈沖耦合神經網絡的裂縫檢測[J];儀器儀表學報;2012年03期
相關博士學位論文 前2條
1 陳進;高光譜圖像分類方法研究[D];國防科學技術大學;2010年
2 黃鴻;圖嵌入框架下流形學習理論及應用研究[D];重慶大學;2008年
本文編號：2162081
本文鏈接：http://www.wukwdryxk.cn/guanlilunwen/gongchengguanli/2162081.html
