深度学习算法在高光谱影像分类中的应用研究
发布时间：2018-11-16 20:35
【摘要】：高光谱遥感近年来发展迅速在许多领域得到了较好的应用,逐渐成为对地物目标进行定量研究的一种重要方法。由于其光谱分辨率高和图谱合一的特点,令其在地表物质的精细识别及分类等方面具有不可比拟的优势,对高光谱影像进行分类成为高光谱遥感应用研究中的重要环节。高光谱影像数据高维数的特点也给影像分类带来了困难,即对于高维特征数据,在进行监督分类时需要大量带标记训练样本来对分类模型进行训练才能保证分类器的精度,也就是Hughes现象。通常采用降维算法来降低高光谱影像数据的维数被广泛应用到高光谱影像分类中,通过降维的手段可以较好的解决Hughes难题。但常用的降维方法,往往局限在提取像元的浅层特征,不能得到像元的深层特征,这一定程度上限制了分类器的表现。鲁棒的深层特征中往往包含像元的抽象结构信息,这更有利于分类精度的提高。本文将深度学习应用到高光谱影像分类中,尝试提取更有利于分类的像元深度特征,同时分析三种常用深度学习算法的优势和特点,着重研究将非监督学习的堆栈式自编码器和深度信念网运用于高光谱影像像元的特征提取中来解决Hughes难题。研究流程为:首先证明高光谱影像中像元的非线性特性和分类时Hughes现象的发生以论证深度学习在高光谱影像分类中的适用性;其次通过与传统降维方法进行类比分析,得出深度学习理论中的自编码器和受限波兹曼机两种特征提取算法性能优于传统算法;然后采用模型参数调优,可视化分析,连接不同分类器下的精度评价等实验方法综合分析,得到了堆栈式自编码器和深度信念网下的最优分类模型;最终对分类性能更优的堆栈式自编码器进行进一步的优化,即在自编码器中加入稀疏表示的限制条件以及引入GPU并行运算,来进一步提升分类精度和分类速度。本文将深度学习理论引入到高光谱影像分类中,通过非监督的学习方法可利用大量的无标签数据,并且能够提取像元的深度特征。实验证明深度学习算法优于传统的特征提取算法,并得出基于深度学习的最优分类模型,即堆栈式稀疏自编码器,在两种实验数据下分类精度可达到93.41%和94.92%,针对模型训练时间长的问题,采用并行运算的方式可使模型的训练速度提升7倍多。
[Abstract]:Hyperspectral remote sensing has been developed rapidly in many fields in recent years, and has gradually become an important method for quantitative study of ground objects. Because of its high spectral resolution and the unity of spectrum, it has an incomparable advantage in the fine recognition and classification of surface materials, so the classification of hyperspectral images has become an important link in the application of hyperspectral remote sensing. The characteristics of high dimension of hyperspectral image data also bring difficulties to image classification, that is, for high-dimensional feature data, a large number of labeled training samples are needed to train the classification model in order to ensure the accuracy of the classifier. This is the Hughes phenomenon. Usually reducing dimension algorithm to reduce the dimension of hyperspectral image data is widely used in hyperspectral image classification, by reducing the dimension of the method can solve the problem of Hughes. However, the commonly used dimensionality reduction methods are often limited in extracting shallow features of pixels, and can not obtain the deep features of pixels, which limits the performance of classifiers to some extent. Robust deep features often contain abstract structure information of pixels, which is more conducive to the improvement of classification accuracy. This paper applies depth learning to hyperspectral image classification, tries to extract pixel depth features that are more favorable to classification, and analyzes the advantages and characteristics of three commonly used depth learning algorithms. This paper focuses on the application of unsupervised learning stack self-encoder and depth belief net to feature extraction of hyperspectral image pixels to solve the Hughes problem. The research flow is as follows: firstly, the nonlinear characteristics of pixels in hyperspectral images and the occurrence of Hughes phenomenon in classification are proved to demonstrate the applicability of depth learning in hyperspectral image classification. Secondly, through the analogy analysis with the traditional dimensionality reduction method, it is concluded that the performance of the self-encoder and the constrained Boltzmann algorithm in the depth learning theory is better than the traditional algorithm. Then the optimal classification model under stack self-encoder and depth belief net is obtained by comprehensive analysis of model parameter tuning visual analysis and precision evaluation under different classifiers. Finally, the stack self-encoder with better classification performance is further optimized, that is, adding the constraint condition of sparse representation to the self-coder and introducing GPU parallel operation to further improve the classification accuracy and classification speed. In this paper, depth learning theory is introduced into hyperspectral image classification. Through unsupervised learning method, a large number of untagged data can be used, and depth features of pixels can be extracted. Experimental results show that the depth learning algorithm is superior to the traditional feature extraction algorithm, and the optimal classification model based on depth learning, i.e. stack sparse self-encoder, can achieve the classification accuracy of 93.41% and 94.92% under two kinds of experimental data. In view of the long training time of the model, the training speed of the model can be increased more than 7 times by parallel operation.
【学位授予单位】：成都理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：P237
[Abstract]:Hyperspectral remote sensing has been developed rapidly in many fields in recent years, and has gradually become an important method for quantitative study of ground objects. Because of its high spectral resolution and the unity of spectrum, it has an incomparable advantage in the fine recognition and classification of surface materials, so the classification of hyperspectral images has become an important link in the application of hyperspectral remote sensing. The characteristics of high dimension of hyperspectral image data also bring difficulties to image classification, that is, for high-dimensional feature data, a large number of labeled training samples are needed to train the classification model in order to ensure the accuracy of the classifier. This is the Hughes phenomenon. Usually reducing dimension algorithm to reduce the dimension of hyperspectral image data is widely used in hyperspectral image classification, by reducing the dimension of the method can solve the problem of Hughes. However, the commonly used dimensionality reduction methods are often limited in extracting shallow features of pixels, and can not obtain the deep features of pixels, which limits the performance of classifiers to some extent. Robust deep features often contain abstract structure information of pixels, which is more conducive to the improvement of classification accuracy. This paper applies depth learning to hyperspectral image classification, tries to extract pixel depth features that are more favorable to classification, and analyzes the advantages and characteristics of three commonly used depth learning algorithms. This paper focuses on the application of unsupervised learning stack self-encoder and depth belief net to feature extraction of hyperspectral image pixels to solve the Hughes problem. The research flow is as follows: firstly, the nonlinear characteristics of pixels in hyperspectral images and the occurrence of Hughes phenomenon in classification are proved to demonstrate the applicability of depth learning in hyperspectral image classification. Secondly, through the analogy analysis with the traditional dimensionality reduction method, it is concluded that the performance of the self-encoder and the constrained Boltzmann algorithm in the depth learning theory is better than the traditional algorithm. Then the optimal classification model under stack self-encoder and depth belief net is obtained by comprehensive analysis of model parameter tuning visual analysis and precision evaluation under different classifiers. Finally, the stack self-encoder with better classification performance is further optimized, that is, adding the constraint condition of sparse representation to the self-coder and introducing GPU parallel operation to further improve the classification accuracy and classification speed. In this paper, depth learning theory is introduced into hyperspectral image classification. Through unsupervised learning method, a large number of untagged data can be used, and depth features of pixels can be extracted. Experimental results show that the depth learning algorithm is superior to the traditional feature extraction algorithm, and the optimal classification model based on depth learning, i.e. stack sparse self-encoder, can achieve the classification accuracy of 93.41% and 94.92% under two kinds of experimental data. In view of the long training time of the model, the training speed of the model can be increased more than 7 times by parallel operation.
【学位授予单位】：成都理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：P237
【参考文献】
相关期刊论文 前10条
1 方敏;王君;王红艳;李天涯;;应用监督近邻重构分析的高光谱遥感数据特征提取[J];红外与激光工程;2016年10期
2 黄鸿;郑新磊;罗甫林;;融合加权均值滤波与流形重构保持嵌入的高光谱影像分类[J];光子学报;2016年10期
3 李新国;黄晓晴;;一种基于DBN的高光谱遥感图像分类方法[J];电子测量技术;2016年07期
4 戴晓爱;郭守恒;任m，
本文编号：2336576
本文链接：https://www.wllwen.com/kejilunwen/dizhicehuilunwen/2336576.html
