遥感专业外文翻译高光谱遥感信息中的特征提取与应用研究.docx

1、遥感专业外文翻译高光谱遥感信息中的特征提取与应用研究2500单词，3900汉字出处：Du P, Tao F, Hong T. Spectral Features Extraction in Hyperspectral RS Data and Its Application to Information Processing J. Acta Photonica Sinica, 2005, 34(2):293-298.本科毕业设计（论文）中英文对照翻译院（系部） 测绘与国土信息工程学院 专业名称 测绘工程 年级班级 学生姓名 指导老师 2012年6月3日Spectral Features Extr

2、action in Hyperspectral RS Data andIts Application to Information ProcessingOriented to the demands of hyperspectral RS information processing and applications, spectral features in hyperspectral RS image can be categorized into three scales: point scale, block scale and volume scale. Based on the p

3、roperties and algorithms of different features, it is proposed that point scale features can be divided into three levels: spectral curve features, spectral transformation features and spectral similarity measure features. Spectral curve features include direct spectra encoding, reflection and absor

4、ption features. Spectral transformation features include Normalized Difference of Vegetation Index (NDV I) , derivate spectra and other spectral computation features. Spectral similarity measure features include spectral angle ( SA ) , Spectral Information Divergence ( SID ) , spectral distance, cor

5、relation coefficient and so on. Based on analysis to those algorithms, several problems about feature extraction, matching and application are discussed further, and it p roved that quaternary encoding, spectral angle and SID can be used to information processing effectively.1 IntroductionHyperspect

6、ral Remote Sensing was one of the most important breakthroughs of Earth Observation System ( EOS) in 1990 s. It overcomes the limitations of conventional aerial and multispectral RS such as less band amount, wide band scope and rough spectral information expression, and can provide RS information wi

7、th narrow band width, more band amount and fine spectral information, also it can distinguish and identify ground objects from spectral space, so hyperspectral RS has got wide applications in resources, environment, city and ecological fields. Because hyperspectral RS is different from conventional

8、RS information obviously in both information acquisition and information processing, there are many problems should be solved in practice. One of the most important problems is about spectral features extraction and application in hyperspectral RS data including hyperspectral RS image and standard s

9、pectral database. Nowadays, studies on hyperspectral are mainly focused on band selection and dimensionality reduction, image classification, mixed pixel decomposition and others, and studies on spectral features are few. In this paper, spectral features extraction and application will be taken as o

10、ur central topic in order to provide some useful advices to hyperspectral RS applications.2 Framework of spectral features in hyperspectral RS dataIn general, hyperspectral RS image can be expressed by a spatial-spectral data cube ( Fig. 1). In this data cube, every coverage expressed the image of o

11、ne band, and each pixel forms a spectral vector composed of albedo of ground object on every band in spectral dimension, and that vector can be visualized by spectral curve ( Fig. 2 ). Many features can be extracted from spectral vector or curve, and spectral features are the key and basis of hypers

12、pectral RS applications. Also each spectral curve in spectral database can be analyzed with same method. Although there are some algorithms to compute spectral features, the framework and system is still not obvious, so we would like to propose a framework for spectral features in hyperspectral RS d

13、ata including hyperspectral RS image and standard spectral database. Fig. 1Hyperspectral image data cube Fig. 2Reflectance spectral curve of a pixel2. 1Three scales of spectral featuresAccording to the operational objects of extraction algorithms, spectral features can be categorized into three scal

14、es: point-scale, block-scale and volume-Scale.Point scale takes pixel and its spectral curve as operational object and some useful features can be extracted from this spectral vector (or spectral curve).In general, hyperspectral RS image takes spectral vector of each pixel as processing object.Block

15、 scale is oriented image block or region. Block is the set of some pixels, and it can be homogeneous or heterogeneous. Homogeneous regions are got by image segmentation and pixels in this region are similar in some given features; heterogeneous region are those image blocks with regular or irregular

16、 size, and they are cut from original image directly, for example, an image can be segmented according to quadtree method. In hyperspectral RS image, block scale features can be computed from two aspects. One is to compute texture feature of a block on some characterized bands, and the other is to c

17、ompute spectral feature of a block. If the block is homogeneous its mean vector can be computed firstly and then spectral of this mean vector can be extracted to describe the block. If the block is heterogeneous, it can be segmented to some homogeneous blocks.Volume scale combines spatial and spectr

18、al features in a whole and extracts features in 3D ( row, column and spectra ) space. Here, some 3D operational algorithms are needed, for example, 3D wavelet transformation and high order Artificial Neural Network (ANN ). Because this type of features is difficult to compute and analyze, we dont re

19、search it in current studies.In this paper, we would like to focus on point scale feature, or those features extracted from spectral vector that may be spectral vector of a pixel or mean vector of a block.2. 2Three levels of point scale featuresFrom operation object, algorithm principles, feature pr

20、operties, application modes and other aspects, we think it is feasible to categorize spectral features into three levels: spectral curve features, spectral transformation features and spectral similarity measure features. They are corresponding to analysis on spectral curve with all bands, data tran

21、sformation and combination with part of all bands and similarity measure of spectral vectors. In our study, data from OM IS and PHI hyperspectral image, USGS spectral database and typical spectra data in China is experimented and two examples are given in this paper. One is to select three regions f

22、rom PH I image (Region I is vegetation, Region II is built-up land, and Region III is mixed region of some land covers) , and the other is spectral curve of three ground objects from USGS spectral database, among them S1 is Actinolite_HS22. 3B, S2 is Actinolite_HS116. 3B and S3 is Albite_HS66. 3B, s

23、o S1 and S2 are similar and they are different from S3.3Spectra l curve featuresSpectral curve features are computed by some algorithms based on the spectral curve of certain pixel or ground object, and it can describe shape and properties of the curve. The main methods include direct encoding and f

24、eature band analysis.3. 1Direct encodingThe important idea of spectral curve feature is to emphasize spectral curve shape, so direct encoding is a very convenient method, and binary encoding is used more widely. Its principle is to compare the attribute value at each band of a pixel with a threshold

25、 and assign the code of“0”or“1”according to its value. That can be expressed byHere, is code of the ith band, is the original attribute value of this band, and T is the threshold. Generally, threshold is the mean of spectral vector, and it can also be selected by manual method according to curve sha

26、pe, sometimes median of spectral vector is probably used. Only one threshold is used in binary encoding, so the divided internal is large and precision is low. In order to improve the appoximaty and precision, the quaternary encoding strategy is proposed in this paper. Its primary idea is as follows

27、: ( 1 ) the mean of the total pixel spectral vector is computed and denoted by T0 , and the attribute is divided into two internal including , and ,; (2) the pixels located in the two internals are determined and the mean of each internal is got and donated by and TR , so four internals are formed i

28、ncluding , TL , , TR and TR ,; ( 3) each band is assigned one of the code sets 0, 1, 2, 3 according to the internal it is located; (4) to compute the ratio of matched bands number to the total band number as final matching ratio. It p roved that quaternary encoding could describe the curve shape mor

29、e precisely.If quarternary encoding is used, the ratio of the same region is smaller than binary encoding, but the ratio between different regions decreased dramatically. So quarternary encoding is more effective in measuring the similarity between different pixels. Because direct encoding will disp

30、erse the continuous albedo into discrete code, the encoding result is affected by threshold obviously and will lead to information loss. Although its operation is very simple, it is only used to some applications requiring low precision, and the threshold should be selected according to different co

31、nditions.3. 2Spectral absorption or reflection featureDiffering from direct encoding in which all bands are used, spectral absorption or reflection feature only emphasizes those bands where valleys or apexes are located. That means those bands with local maximum or minimum in spectral curve should b

32、e determined at first and then further analysis can be done. In general, albedo is used to describe the attribute of a pixel, so those bands with local maximum are reflection apex and those with local minimum are absorption valley.After the location and related parameters are got, the detail analysis can be done. In general two methods are used, one is to give direct encoding and analysis to feature bands, and the other is to compute some quantitative index using feature bands and their parameters.3.3Encoding of spectra l absorption or reflect