本文選題：高光譜 + 城市場(chǎng)景��； 參考：《哈爾濱工業(yè)大學(xué)》2014年碩士論文

【摘要】：高光譜技術(shù)是近幾十年來(lái)地球觀測(cè)技術(shù)取得的最重大成就之一。高光譜圖像光譜分辨率較高，能夠提供非常豐富的光譜信息，因此在許多領(lǐng)域得到了廣泛應(yīng)用，但是由于空間分辨率較低，在用來(lái)對(duì)城市場(chǎng)景進(jìn)行分析時(shí)受到很大限制。城市中場(chǎng)景的面積較小且分布密集，使用低空間分辨率的圖像不能有效區(qū)分地物。隨著高光譜傳感器技術(shù)的發(fā)展，高光譜圖像的空間分辨率有了較大提升，許多小區(qū)域場(chǎng)景能夠由像素來(lái)描述，使得利用高空間-高光譜分辨率的遙感圖像對(duì)城市場(chǎng)景進(jìn)行分析成為可能。本文將利用具有較高空間分辨率的高光譜圖像對(duì)城市場(chǎng)景進(jìn)行分類識(shí)別研究。具體工作內(nèi)容如下： 首先，根據(jù)高光譜圖像的數(shù)據(jù)特性進(jìn)行光譜特征提取。在采用傳統(tǒng)的局部Fisher判別分析方法和近鄰保留嵌入方法的基礎(chǔ)上，將二者結(jié)合起來(lái)，提出了一種半監(jiān)督局部判別分析方法。本方法綜合考慮了已知樣本的可分性信息和未知樣本的結(jié)構(gòu)信息。基于該方法對(duì)城市場(chǎng)景的光譜特征進(jìn)行提取，利用支持向量機(jī)和最大似然方法進(jìn)行分類，通過(guò)與其他特征提取算法進(jìn)行對(duì)比分析，驗(yàn)證了半監(jiān)督局部判別分析方法提取特征的分類效果。 然后，利用城市高光譜圖像的高空間分辨率特點(diǎn)，提取空間特征，包括形態(tài)學(xué)特征、形狀特征等。進(jìn)而對(duì)空譜特征的聯(lián)合方式進(jìn)行了重點(diǎn)研究，主要采用以下三種方式：第一，直接對(duì)光譜和空間特征進(jìn)行組合；第二，采用基于核函數(shù)的特征組合方式，將不同的特征在核變換空間進(jìn)行組合；第三，采用多特征組合框架對(duì)特征進(jìn)行組合，對(duì)不同特征進(jìn)行降維，通過(guò)保留盡可能多的信息來(lái)實(shí)現(xiàn)組合。使用單種特征和各種空譜聯(lián)合特征進(jìn)行支持向量機(jī)分類實(shí)驗(yàn)，結(jié)果表明空譜聯(lián)合特征會(huì)提升光譜或空間特征的分類精度。 最后，針對(duì)城市場(chǎng)景分類識(shí)別中可能存在的訓(xùn)練樣本不足問(wèn)題，，結(jié)合主動(dòng)學(xué)習(xí)方法進(jìn)行了研究，并利用判別隨機(jī)場(chǎng)模型對(duì)分類結(jié)果進(jìn)行優(yōu)化。在傳統(tǒng)主動(dòng)學(xué)習(xí)算法的基礎(chǔ)上，利用已知樣本信息，提出了一種確定候選樣本集的方法。該方法最大的優(yōu)勢(shì)在于主動(dòng)學(xué)習(xí)的過(guò)程中不需要人工標(biāo)記選出的新樣本。論文還針對(duì)歸屬類別概率的輸出問(wèn)題，研究了一種基于邏輯回歸模型的多項(xiàng)式邏輯回歸分類方法。通過(guò)使用多項(xiàng)式邏輯回歸方法和支持向量機(jī)對(duì)提出的確定候選集的方法進(jìn)行了驗(yàn)證，實(shí)驗(yàn)表明該方法不但節(jié)省了人力消耗，而且可以在小樣本情況下有效提高分類精度。
[Abstract]:Hyperspectral technology is one of the most important achievements in Earth observation technology in recent decades. Hyperspectral images have high spectral resolution and can provide rich spectral information, so they are widely used in many fields. However, because of their low spatial resolution, they are limited in analyzing urban scenes. Because of the small area and dense distribution of the scene in the city, the low spatial resolution image can not effectively distinguish the ground objects. With the development of hyperspectral sensor technology, the spatial resolution of hyperspectral images has been greatly improved, many small regional scenes can be described by pixels. It is possible to use high spatial and hyperspectral resolution remote sensing images to analyze urban scenes. In this paper, hyperspectral images with high spatial resolution are used to classify and recognize urban scenes. The main work is as follows: firstly, spectral feature extraction is carried out according to the data characteristics of hyperspectral image. Based on the traditional local Fisher discriminant analysis method and the nearest neighbor retention embedding method, a semi-supervised partial discriminant analysis method is proposed. In this method, the separability information of known samples and the structural information of unknown samples are considered. Based on this method, the spectral features of urban scenes are extracted. Support vector machine (SVM) and maximum likelihood method are used to classify and compare with other feature extraction algorithms. The classification effect of the discriminant analysis method is verified. Then, the spatial features, including morphological features and shape features, are extracted by using the high spatial resolution of urban hyperspectral images. Then, the paper focuses on the joint method of space-spectrum features, mainly using the following three ways: first, the spectral and spatial features are combined directly; second, the kernel-based feature combination method is adopted. The different features are combined in kernel transform space. Thirdly, multi-feature combination framework is used to combine the features, reduce the dimension of different features, and achieve the combination by retaining as much information as possible. The support vector machine (SVM) classification experiment is carried out by using a single feature and a variety of space-spectrum joint features. The results show that the space-spectrum joint feature can improve the classification accuracy of spectral or spatial features. Finally, aiming at the problem of insufficient training samples in urban scene classification and recognition, combining with active learning method, the classification results are optimized by discriminant random field model. Based on the traditional active learning algorithm and using the known sample information, a method to determine the candidate sample set is proposed. The biggest advantage of this method is that it does not need to mark the new samples in the process of active learning. A polynomial logistic regression classification method based on logical regression model is also studied in this paper. The polynomial logic regression method and support vector machine are used to verify the proposed method to determine the candidate set. The experimental results show that the proposed method not only saves manpower consumption, but also can effectively improve the classification accuracy in the case of small samples.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 黃昕;李平湘;張良培;;基于多層形狀特征提取與融合的城市高光譜影像解譯[J];測(cè)繪科學(xué);2009年06期

2 王志勇,劉文奇;基于數(shù)學(xué)形態(tài)學(xué)的快速運(yùn)動(dòng)物體檢測(cè)[J];計(jì)算機(jī)工程與科學(xué);2005年01期

3 劉康;錢旭;王自強(qiáng);;主動(dòng)學(xué)習(xí)算法綜述[J];計(jì)算機(jī)工程與應(yīng)用;2012年34期

本文編號(hào)：2101020