本文關鍵詞：基于卷積神經(jīng)網(wǎng)的高光譜數(shù)據(jù)特征提取及分類技術研究　出處：《哈爾濱工業(yè)大學》2016年碩士論文　論文類型：學位論文

  更多相關文章： 高光譜圖像 深度學習 卷積神經(jīng)網(wǎng)絡 特征提取 分類

【摘要】：基于高光譜數(shù)據(jù)的特征提取及分類技術一直是遙感領域研究的熱點問題之一,而現(xiàn)有的特征提取方法主要針對地物某一方面的特性,利用線性或非線性的方程人為地設計或指定提取的特征,這種人工選取特征的過程往往需要專業(yè)的知識和經(jīng)驗,并且需要花費大量的時間,然而提取的特征并不能充分表達高光譜數(shù)據(jù)復雜的內(nèi)部結構和空譜信息。對于深度學習來說,它可以讓計算機自動地學習有利于任務需要的特征,并將該過程融入模型訓練的一部分,從而有助于進一步提高分類識別精度。本篇論文從高光譜數(shù)據(jù)的特點入手,結合基于深度學習的卷積神經(jīng)網(wǎng)絡模型,利用多個卷積層和池化層從高光譜數(shù)據(jù)中提取對多種變形具有高度不變性的非線性特征,進而實現(xiàn)高光譜數(shù)據(jù)的地物分類。本文的主要研究內(nèi)容及成果包括以下幾個方面:首先,針對高光譜遙感數(shù)據(jù)圖譜合一的特點,探究深層卷積網(wǎng)絡對高光譜數(shù)據(jù)特征提取及分類的適用性。高光譜數(shù)據(jù)在獲取拍攝面的空間信息時,可以獲得每一個像素的連續(xù)光譜曲線,這使得高光譜數(shù)據(jù)擁有較高的維度和較大的數(shù)據(jù)量,而深度學習的模型正適用于該數(shù)據(jù)的特點。因此本文使用高光譜數(shù)據(jù)的光譜信息、空間信息和空譜聯(lián)合信息,分別構造基于一維、二維和三維卷積核的深層卷積神經(jīng)網(wǎng)絡,實現(xiàn)了特征分級式表達,并將提取的特征引入高光譜數(shù)據(jù)的地物分類中,得到優(yōu)于其他特征提取及分類方法的結果。其次,針對數(shù)據(jù)高維度與有限訓練樣本的不均衡問題,本文分別在一維卷積模型中引入L2正則項修改原始代價函數(shù),在二維和三維模型中加入Dropout層稀疏每層網(wǎng)絡的激活單位,來避免建模過程中過擬合現(xiàn)象的發(fā)生。并利用非飽和的非線性函數(shù)Re LU代替原有的Sigmoid激活函數(shù),大大提高模型的收斂速度,降低了模型的復雜度。最后,在較少的訓練樣本下,基于光譜信息的一維深層卷積模型并不能提供穩(wěn)定的分類結果,為了進一步提高模型的分類性能,本文提出了基于隨機特性選擇的深度卷積神經(jīng)網(wǎng)絡集成模型。從兩組數(shù)據(jù)的實驗結果表明,與其他分類方法的分類精度相比,該方法是一個較有競爭力的解決方案。
[Abstract]:Based on the feature extraction and classification of hyperspectral data has been one of the hot issues in the field of remote sensing research, and the existing methods of feature extraction for the main features of a certain objects, using linear or nonlinear equations artificially specified design or feature extraction, the artificial feature selection process often requires professional knowledge and experience. And the need to spend a lot of time, however, the extracted features and can not fully express the internal structure information of hyperspectral data and complicated spatial spectrum. For deep learning, it allows the computer to automatically learn features that are beneficial to the needs of tasks, and integrate the process into part of model training, which is helpful to further improve the accuracy of classification and recognition. This paper starts from the characteristic of hyperspectral data, based on convolutional neural network model based on deep learning, using a multi layer and pool layer extraction volume is highly nonlinear deformation characteristics of multiple invariance from hyperspectral data, so as to realize the classification of hyperspectral data. The main contents and achievements of this paper include the following aspects: first, aiming at the characteristics of hyperspectral remote sensing data, we explore the applicability of deep convolution network to hyperspectral data feature extraction and classification. Hyperspectral data can get continuous spectral curves of each pixel when acquiring the spatial information of the shooting surface, which makes the hyperspectral data have higher dimension and larger data volume, while the deep learning model is suitable for the characteristics of the data. The spectral information and spatial information and it is the use of hyperspectral data with spectral information, we construct one-dimensional, two-dimensional and three-dimensional convolution kernel deep convolutional neural network based on the expression characteristics of hierarchical, and feature extraction of hyperspectral data into object classification, feature extraction and classification is better than that by other methods the results of. Secondly, aiming at the problem of unbalanced data in high dimension and limited training samples, this paper in the convolution model introduced by L2 regularization to modify the original cost function, activation of Dropout units into each layer of the network layer is sparse in 2D and 3D model, to avoid the overfitting phenomenon in the process of modeling. And using the unsaturated nonlinear function Re LU instead of the original Sigmoid activation function, the convergence speed of the model is greatly improved and the complexity of the model is reduced. Finally, under a few training samples, the one-dimensional deep convolution model based on spectral information can not provide stable classification results. In order to further improve the classification performance of the model, a deep convolution neural network ensemble model based on random feature selection is proposed in this paper. The experimental results from two sets of data show that this method is a more competitive solution compared with the classification accuracy of other classification methods.
【學位授予單位】：哈爾濱工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP751;TP183
，

本文編號：1343820