共查询到20条相似文献，搜索用时 890 毫秒
1.
提出一种稀疏自表达方法来研究高光谱影像分类中的波段选择问题。该方法利用字典矩阵等于测量矩阵的条件来改进多观测向量的稀疏表达模型,将波段子集看作高光谱影像波段集合中的代表子集。稀疏自表达方法将波段选择转换为寻求多观测向量中稀疏系数矩阵的非零行向量问题,通过引入混合范数来限定非零元素行向量的个数,利用快速交替方向乘子方法求解稀疏系数矩阵,并聚类非零行向量,实现波段的有效选择。基于两个公开高光谱影像数据集并对比其他4种波段选取方法来验稀疏自表达方法。实验结果证明,稀疏自表达方法能够在计算效率明显优于基于波段相关性的线性限制最小方差方法的同时,取得与该方法和非负稀疏矩阵分解方法相匹甚至略高的总体分类精度。 相似文献
2.
高光谱影像波段众多且相关性强，导致分类存在信息冗余且计算量较大。提出了可分离非负矩阵分解方法来选取高光谱影像的代表性波段子集，在保证分类精度的同时降低计算量。该方法假设高光谱影像的波段集合具有可分离特性，改进传统非负矩阵分解模型，将波段选择转换为可分离非负矩阵分解问题，采用迭代投影方法来依次选取能够非负线性表达其他波段的代表性波段。在此基础上，利用两个公开高光谱数据集对比几种主流方法，采用定量评价和分类精度指标来综合评价所提的波段选择方法的效果。实验结果表明，可分离非负矩阵分解方法的分类精度高于其他几种方法，而且计算效率排名第2，能够选取合适的波段子集以满足高光谱遥感的应用需求。 相似文献
3.
4.
针对高光谱影像数据中存在大量冗余,传统异常探测算法应用高光谱所有波段进行探测计算量巨大的问题,提出一种基于波段相似性线性预测与学习字典的异常探测算法。该算法首先通过对波段的相似性进行线性预测,找到最不相似的波段子集;然后,利用学习字典算法获得能够表征图像背景信息的背景字典,并通过低秩分解的算法将影像分解为低秩矩阵与稀疏矩阵;最后,使用经典RXD(Reed-X detector)探测算法对稀疏影像进行异常探测。实验结果表明,该算法可以在减少计算代价、保持波段原始信息不被破坏的同时,能够较好地实现了高光谱影像的异常探测。 相似文献
5.
非监督波段选择方法是高光谱图像降维的主要方法,但现有方法应用到实际高光谱图像分类时,分类精度并不理想。本文提出一种改进的基于聚类的高光谱图像非监督波段选择方法,主要通过对传统的K-means聚类算法进行两方面改进:一方面是相似性度量函数;另一方面是聚类中心的选取。然后,通过实验数据用支持向量机法(SVM)对所提算法及现有的三种非监督波段选择方法进行分类。最后,用总体精度(OA)和Kappa系数评价分类结果。表明本文所提方法在分类精度方面优于其他现有方法。 相似文献
6.
空间与谱间相关性分析的NMF高光谱解混 总被引：2，自引：1，他引：1
非负矩阵分解(NMF)技术是高光谱像元解混领域的研究热点。为了充分利用高光谱图像中丰富的空间与光谱相关性特征,改善基于NMF的高光谱解混算法性能,提出一种结合了空间与谱间相关性分析的NMF解混算法。算法针对NMF的通用性和局部极小问题,引入并结合高光谱图像两种典型的相关性特征,具体包括:基于马尔可夫随机场(MRF)模型,建立描述相邻像元空间相关特征的约束;通过复杂度映射技术,建立描述相邻波段谱间相关(光谱分段平滑)特征的约束;并将上述两种约束同时引入NMF解混目标函数中。实验结果表明,对于一般自然地物场景或人造地物场景,相对于分段平滑和稀疏约束的非负矩阵分解(PSNMFSC)、交互投影子梯度的非负矩阵分解(APSNMF)和最小体积约束的非负矩阵分解(MVCNMF)这3种代表性NMF解混参考算法,该算法可进一步提高高光谱解混精度;对于空间相关或谱间相关特征中某一种不显著的特殊场景,也具有更好的适应能力。通过将空间相关和谱间相关特征相结合,较全面地反映了高光谱数据与解混相关的重要特征,能够对绝大多数真实高光谱数据进行高精度解混,对高光谱解混及后续应用领域相关研究均具有参考价值。 相似文献
7.
高光谱遥感影像具有光谱分辨率极高的特点,承载了大量可区分不同类型地物的诊断性光谱信息以及区分亚类相似地物之间细微差别的光谱信息,在目标探测领域具有独特的优势。与此同时,高光谱遥感影像也带来了数据维数高、邻近波段之间存在大量冗余信息的问题,高维度的数据结构往往使得高光谱影像异常目标类和背景类之间的可分性降低。为了缓解上述问题,本文提出了一种基于波段选择的协同表达高光谱异常探测算法。首先,使用最优聚类框架对高光谱波段进行选择,获得一组波段子集来表示原有的全部波段,使得高光谱影像异常目标类与背景类之间的可分性增强。然后使用协同表达对影像上的像元进行重建,由于异常目标类和背景类之间的可分性增强,对异常目标像元进行协同表达时将会得到更大的残差,异常目标像元的输出值增大,可以更好地实现异常目标和背景类的分离。本文使用了3组高光谱影像数据进行异常目标探测实验,实验结果表明,该方法与其他现有高光谱异常目标探测算法对比,曲线下面积AUC(Area Under Curve)值更高,可以更好地实现异常目标与背景分离,能够更有效地对高光谱影像进行异常目标探测。 相似文献
8.
讨论了信息熵和均匀光谱间隔(USS)两种无监督高光谱影像波段选择方法,分析比较了基于K均值聚类的欧氏距离、相关系数以及光谱角3种相似性度量。实验表明,利用USS对高光谱影像降维,采用将欧氏距离作为相似性度量的K均值聚类方法进行影像分类,所得到的分类结果精度较高,计算时间较短。 相似文献
9.
高光谱遥感影像波段众多、相关性强,导致其实际分类应用计算量大且存在明显的"维数灾难"问题。本文提出加权概率原型分析方法来研究高光谱影像的波段选择问题。该方法考虑波段间的差异性,引入综合差异性度量指标来构造权重矩阵以改进传统原型分析模型;考虑稀疏系数的狄利克雷分布和高光谱成像过程的量子特性,引入贝叶斯框架理论来构建波段选择的优化模型。加权概率原型分析方法采用迭代优化的策略,利用交替方向乘积方法来依次求解两个凸优化子问题来得到局部最优的稀疏系数矩阵并实现波段子集的最优估计。基于两个公开的高光谱数据集,对比4种主流的波段选择方法(SpaBS、SNMF、ISSC、SSR)来验证提出方法的可靠性。实验结果表明,加权概率原型分析方法的总体分类精度高于其他4种方法,能够得到更好的分类结果图。本文提出的加权概率原型分析模型能够选择合适的波段子集来满足高光谱影像的高精度分类需求。 相似文献
10.
《国土资源遥感》2018,(4)
为了减少混合像元对字典建立的影响,结合在线字典学习法与主成分分析(principal component analysis,PCA)法提取全色与各分解影像字典的第一主成分分量构成PCA联合稀疏字典。该字典包括多光谱影像特征与高空间分辨率影像特征,同时考虑到了混合像元问题。使用PCA联合稀疏字典进行正交匹配追踪法(orthogonal matching pursuit,OMP)计算,分别得到全色与多光谱影像的稀疏系数,采用非负矩阵分解(nonnegative matrix factor,NMF)融合算法得到融合影像的稀疏系数,进行重构生成融合影像。对字典矩阵大小的研究,考虑到重构图像的均方根误差与计算机运算的限制,最终确定稀疏字典矩阵大小为64像元×480像元。采用5种定量融合评定指标对本文方法与联合字典NMF方法、小波方法和PCA方法的影像融合结果进行分析比较,结果表明本文方法既可提高融合影像的纹理细节信息,也能较好地保持多光谱信息,获得更好的融合效果。 相似文献
11.
12.
银川平原土壤盐渍化与中低产田遥感应用研究 总被引：10，自引：0，他引：10
土壤盐渍化是影响农业生产与生态环境的一个重要因素。长期以来,宁夏银川平原的次生土壤盐渍化问题十分突出,形成了许多盐渍型中低产田,影响和制约了区域农业的可持续发展。主要采用遥感解译方法提取了银川平原土壤盐渍化的分类与分布的现状信息。在此基础上,依据中低产田的分类标准,将相关的耕地类型、土壤肥力、作物产量、灌排水指标等因子转化成数字化专题图层,采用多源信息复合分类的方法,通过“综合分析,主导因子判定”实现了GIS辅助下的中低产田分类,为遥感和地理信息系统技术在土壤盐渍化和中低产田调查研究中的应用,探索出了一条可行的途径。 相似文献
13.
Wolf-Dieter Rase 《Journal of Geographical Systems》2001,3(2):199-213
The interpolation of continuous surfaces from discrete points is supported by most GIS software packages. Some packages provide
additional options for the interpolation from 3D line objects, for example surface-specific lines, or contour lines digitized
from topographic maps. Demographic, social and economic data can also be used to construct and display smooth surfaces. The
variables are usually published as sums for polygonal units, such as the number of inhabitants in communities or counties.
In the case of point and line objects the geometric properties have to be maintained in the interpolated surface. For polygon-based
data the geometric properties of the polygon boundary and the volume should be preserved, avoiding redistribution of parts
of the volume to neighboring units during interpolation. The pycnophylactic interpolation method computes a continuous surface
from polygon-based data and simultaneously enforces volume preservation in the polygons. The original procedure using a regular
grid is extended to surface representations based on an irregular triangular network (TIN).
Received: 5 October 2000 / Accepted: 20 December 2000 相似文献
14.
W. Andrew Marcus 《Journal of Geographical Systems》2002,4(1):113-126
Maximum likelihood supervised classifications with 1-m 128 band hyperspectral data accurately map in-stream habitats in the
Lamar River, Wyoming with producer's accuracies of 91% for pools, 87% for glides, 76% for riffles, and 85% for eddy drop zones.
Coarser resolution 5-m hyperspectral data and 1-m simulated multiband imagery yield lower accuracies that are unacceptable
for inventory and analysis. Both high spatial resolution and hyperspectral coverage are therefore necessary to map microhabitats
in the study area. In many instances, the high spatial resolution hyperspectral (HSRH) imagery appears to map the stream habitats
with greater accuracy than our ground-based surveys, thus challenging classical approaches used for accuracy assessment in
remote sensing.
Received: 9 April 2001 / Accepted: 8 October 2001 相似文献
15.
基于RS和GIS的桓仁县乡村聚落景观格局分析 总被引：18，自引：1，他引：17
运用RS和GIS技术以及景观分析方法,以辽东山区桓仁县典型的6个乡镇乡村聚落为研究对象,选取乡村聚落斑块数、斑块面积、斑块密度、平均斑块面积、面积加权平均斑块分维数等5个景观指数,从乡村聚落用地、规模、形态、分离度4个方面进行景观空间格局分析.结果表明,桓仁县乡村聚落的景观格局具有用地比重偏少,聚落斑块数量多、平均斑块面积小,聚落规模在0.743～1.292hm2之间,形态分布稀疏零散,分形指数小、斑块稳定,分离度大等特点.说明在这种乡村聚落景观格局作用下,必然导致自然景观缺乏高度连接,聚落周边自然生态环境受到侵扰和破坏. 相似文献
16.
Whereas for commuting travel there is a one-to-one correspondence between commuters and jobs, and for commodity flows a one-to-one
correspondence between the size of orders and the shipping cost of the commodities, the situation is much more complex for
retail/service travel. A typical shopper may make a single trip or multi-stop tour to buy/consume a quite diverse set of commodities/services
at different locations in quite variable quantities. At the same time, the general pattern of the tour is clearly dependent
on the activities and goods available at potential stops. These interdependencies have been alluded to in the literature,
especially by spatial economists. However, until some preliminary work by the first author, there has been no attempt to formally
include these interdependencies in a general model. This paper presents a framework for achieving this goal by developing
an evolutionary set of models starting from the simplest forms available. From the above, it is clear that such interdependency
models will inevitably have high dimensionality and combinatorial complexity. This rules out a simultaneous treatment of all
the events using an individual choice approach. If an individual choice approach is to be applied in a tractable manner, the
set of interdependent events needs to be segmented into several subsets, with simultaneity recognised within each subset,
but a mere sequential progression occurring between subsets. In this paper, full event interdependencies are retained at the
expense of modelling market segments of consumers rather than a sample of representative individuals. We couple the travel
and consumption events in the only feasible way, by modelling the tours as discrete entities, in conjunction with the amount
of each commodity consumed per stop on each such tour in terms of the continuous quantities of microeconomics. This is performed
both under a budget/income constraint from microeconomics and a time budget constraint from time geography. The model considers
both physical trips and tele-orders.
Received: 14 August 2000 / Accepted: 6 October 2001 相似文献
17.
18.
Recent advances in accessibility research: Representation,methodology and applications 总被引：22，自引：0，他引：22
Mei-Po Kwan Alan T. Murray Morton E. O'Kelly Michael Tiefelsdorf 《Journal of Geographical Systems》2003,5(1):129-138
In this article we examine recent advances in accessibility research and their implications for future studies. We base our
discussion on three intersecting dimensions that are useful for evaluating the contribution of recent studies: representation,
methodology and applications. Various examples are selected to show that research concerned with representation and methodological
problem solving is often applied to issues of broad concern in policy and planning. It is, however, not clear that the simultaneous
treatment of representation, methodological and application issues has ever been fully worked out. The questions raised in
this article may serve as a foundation for addressing issues pertinent to accurate representation, improved model building,
and more rigorous applications in accessibility research.
Received: 9 December 2002 / Accepted: 10 February 2003 相似文献
19.
Mark L. Wilson 《Journal of Geographical Systems》2002,4(1):31-42
Many infectious diseases that are emerging or transmitted by arthropod vectors have a strong link to landscape features.
Depending on the source of infection or ecology of the transmitting vector, micro-habitat characteristics at the spatial scale
of square meters or less may be important. Recently, satellite images have been used to classify habitats in an attempt to
understand associations with infectious diseases. Whether high spatial resolution and hyperspectral (HSRH) images can be useful
in studies of such infectious diseases is addressed. The nature of questions that such studies address and the desired accuracy
and precision of answers will determine the utility of HSRH data. Need for such data should be based on the goals of the effort.
Examples of kinds of questions and applications are discussed. The research implications and public health applications may
depend on available analytic tools as well as epidemiological observations.
Received: 30 July 2001 / Accepted: 14 October 2001 相似文献