共查询到20条相似文献，搜索用时 343 毫秒
1.
面向对象与卷积神经网络模型的GF-6 WFV影像作物分类 总被引：1，自引：0，他引：1
GF-6 WFV影像是中国首颗带有红边波段的中高分辨率8波段多光谱卫星的遥感影像,对于其影像及红边波段对作物分类影响的研究利用亟待展开。本文结合面向对象和深度学习提出一种适用于GF-6 WFV红边波段的卷积神经网络(RE-CNN)遥感影像作物分类方法。首先采用多尺度分割和ESP工具选择最佳分割参数完成影像分割,通过面向对象的CART决策树消除椒盐现象的同时提取植被区域,并转化为卷积神经网络的输入数据,最后基于Python和Numpy库构建的卷积神经网络模型(RE-CNN)用于影像作物分类及精度验证。有无红边波段的两组分类实验结果表明:在红边波段组,卷积神经网络(RE-CNN)作物分类识别取得了较好的效果,总体精度高达94.38%,相比无红边波段组分类精度提高了2.83%,验证了GF-6 WFV红边波段对作物分类的有效性。为GF-6 WFV红边波段影像用于作物的分类研究提供技术参考和借鉴价值。 相似文献
2.
本文介绍了基于ＢＰ神经网络的遥感模式识别方法的特点，同时引入分形维数的概念及其在图像中的计算和应用，并将分维作为反映各类别数据纹理特征的附加波段分量，加到网络的输入层，明显地提高了分类精度。 相似文献
3.
一个用神经网络优化的针对ASTER数据反演地表温度和发射率的多波段算法 总被引：1，自引：0，他引：1
提出了针对ASTER数据同时反演地表温度和发射率的多波段算法。即利用ASTER数据的第11~14热红外波段建立热辐射传输方程，并同时对相应波段的发射率建立近似线性方程，得到6个方程6个未知数，从而形成了针对ASTER数据的同时反演地表温度和发射率的多通道算法。利用3种方法求解方程： ①先分类，然后进行数学计算； ②利用最小二乘法； ③利用神经网络方法。利用辐射传输模型MODTRAN 4模拟数据进行反演及验证分析，结果表明，神经网络能够提高算法的精度和实用性，反演的地表温度平均误差为0.5 ℃，反演的发射率平均误差分别在0.007(11、12波段)和0.006(13、14波段)以下。 相似文献
4.
基于ASTER数据的决策树自动构建及分类研究 总被引：6，自引：3，他引：6
在对ASTER原始9个波段数据进行各种变换处理的基础上，采用数量化指标平均可分性方法确定参与分类的最佳特征组合； 结合研究区8种主要地物类型训练数据集，分别采用最大似然法、BP神经网络法和基于See 5.0数据挖掘的决策树分类法进行分类，提取主要地物的空间分布专题信息。经过379个野外样点的验证，结果表明： 决策树算法分类性能最优，神经网络算法次之，最大似然法效果最差； 与ENVI 4.1、ERDAS 8.7提供的传统决策树建立及分类方法比较，基于数据挖掘工具See 5.0和Cart的决策树生成和分类方法具有客观、高效率、分类性能可靠和精度高等优点。 相似文献
5.
基于神经网络方法的极化雷达地表参数反演 总被引：6，自引：1，他引：6
人工神经网络（Artificial Neural Network)是一个由独立处理单元以一定拓扑结构高度连接而成的并行分布式信息处理结构，适于解决各种非线性问题，积分方程（Integrated Equation Model)单散射模型可模拟各种地表参数条件下裸露地表后向散射系数，以IEM为基础生成训练数据，用L波段的C波段SIR-CHH，VV极化单散射后向散射系数数据为神经网络输入，通过后向反馈（BP）神经网络模型可同时反演得到裸露地表条件下地表介电常数，地表相关长度和均方根高度等地表参数。 相似文献
6.
为了实现地物精准分类,需要有效地提取与分析高光谱遥感图像中丰富的空—谱信息。提出一种适用于高光谱遥感图像分类的变异系数与卷积神经网络相结合(CV-CNN)的方法。这种新方法引入变异系数的思想来衡量高光谱遥感图像不同波段之间的相似性和差异性,从而提出类间变异系数(CVIE)和类内变异系数(CVIA)的概念。通过计算(CVIE)~2/CVIA的值来剔除高光谱遥感图像中的低效波段,然后提取每个像素的空一谱信息,并对其进行2维矩阵化操作,转化为便于卷积神经网络(CNN)输入的灰度图像,最后采用自行构建的适合于高光谱遥感图像分类的CNN模型进行分类。Indian Pines和Pavia University两组数据的实验结果表明,该方法在两种数据集下的总体精度分别达到98.69%和99.66%,有效地改善了高光谱遥感图像的分类精度。 相似文献
7.
在过去几年里,卷积神经网络已经在高光谱图像分类上取得良好的效果,然而高光谱图像的高维性和卷积神经网络对所有波段的平等处理,限制了这些方法性能。本文提出了一种端到端的光谱空间注意力双边网络SSABN (Spectral-Spatial Attention Bilateral Network),直接将原始图像3D块作为输入数据,而不需要进行预处理。首先,通过光谱空间注意力模块从原始数据中增强有用波段,抑制无效波段。然后,设计双边网络两条路径。其中,空间路径用于提取空间信息,上下文路径用于提供更大的感受野,并通过特征融合模块有效的结合特征。实验结果表明,SSABN在3个公开数据集上取得了更高的分类精度,同时有效的减少训练时间。 相似文献
8.
针对高光谱影像分类问题，提出了一种显著性特征提取方法。首先，利用超像素分割算法将高光谱影像3个相邻波段分割为若干个小区域。然后，基于分割得到的小区域计算反映不同区域的显著性特征。最后，沿着光谱方向采用大小为3、步长为1的滑窗法获得所有波段的显著性特征。进一步将提取的显著性特征与光谱特征进行结合，并将结合后的特征输入到支持向量机中进行分类。利用Pavia大学、Indian Pines和Salinas 3组高光谱影像数据进行分类试验。试验结果表明，与传统的空间特征提取方法和基于卷积神经网络的高光谱影像分类方法相比，提取的显著性特征能够获得更高的高光谱影像分类精度，且结合光谱特征能够进一步提高分类精度。 相似文献
9.
特征是图像处理中用于辨识目标的最基本属性.提出了利用模糊神经网络方法,针对舰船的几何特征、矩特征和纹理特征进行舰船目标识别处理.首先简单地描述了几何特征、矩特征尤其是Hu矩特征、一阶纹理特征和二阶纹理特征.然后分别对仿真数据、卫星观测数据中的舰船目标,以及自动检测处理获取的舰船目标的几何特征、Hu机特征和纹理特征进行了提取和分析.模糊神经网络方法可以综合模糊集理论和神经网络方法的优势,有效地实现基于特征的图像目标分类识别处理.文章首先描述了一种主从神经元结构的模糊神经网络分类识别方法,然后利用该方法对大型舰船进行分类识别,包括基于单类舰船特征的分类识别和基于多源(时相)数据融合的分类识别.实验结果表明,基于大型舰船的几何特征、矩特征和纹理特征,利用模糊神经网络方法可以实现对大型舰船目标的有效分类识别.通过多源数据融合处理,可以改善分类识别效果. 相似文献
10.
11.
Operationally AVHRR and TM/TM+ data were used and a supervised maximum likelihood classification (MLH) was applied to depict land use changes in Beijing, providing basic maps for planning and development. With rapid growth of the city these are helpful to deal with higher resolution data, whereas new classification algorithms produce land use maps more accurate. In the paper, new sensor ASTER data and the Kohonen self-organized neural network feature map (KSOM) were tested.The TSOM classified 7% more accurately than the maximum likelihood algorithm in general, and 50% more accurately for the classes ‘residential area’ and ‘roads’. The results suggest that ASTER data and the Kohonen self-organized neural network classification can be used as an alternative data and method in a land use update operational system. 相似文献
12.
基于不同分辨率遥感影像的分类方法对比研究 总被引：2，自引：0，他引：2
基于4种不同分辨率的遥感影像数据,分别为30 m分辨率的Landsat-8数据,融合Landsat-8多光谱波段和全色波段的15 m分辨率数据,5.8 m分辨率的资源3号卫星数据以及融合后2.1 m分辨率的资源3号卫星数据。采用ISO-DATA、最大似然分类法和面向对象分类法对影像进行分类,对分类方法的效果以及分辨率变化对面向对象分类方法的精度影响进行分析。结果显示在低分辨率影像中,面向对象方法受到限制,分类效果相比传统方法没有太大改善;而在高分辨率影像中,面向对象方法分类效果很好,并且随着分辨率提高分类精度也相应的提高。 相似文献
13.
及时获取有效的土地覆盖信息是地球系统模拟的基础。因此,中等空间分辨率传感器如MODIS或MERIS空前的通道设置与观测能力,使其具有快速更新土地覆盖图的能力。本文说明了如何结合MERIS的空间维（像元大小为300m）、光谱维（可见光与近红外范围内15个通道）和时间维（重返周期2—3d）,用于获取不同区域土地覆被组分的亚像元级组成权重。利用4月、7月和8月三期MERIS FR1b级数据得到荷兰主要土地覆被类型的组成权重。单一时相和多时相的数据都使用单个像元最优化的端元数进行线性光谱分解。利用一种形态偏离指数得到MERIS的空间维并用于端元的选择。应用荷兰土地利用数据库（LGN5）25m分辨率的栅格数据作为本文的参考数据。基于这种数据的高分辨率,因此可以从像元和亚像元的水平同时评价的分类精度。结果显示,结合4月和7月的影像可以获得最优的分类结果,精度约为58%。总的说来,亚像元和像元级的分类精度相似。通过几种组分类别和日期的光谱融合表明,物候状况对于数据获取时相最佳结合的选择以及正确识别土地覆盖类型的重要性。 相似文献
14.
With the high deforestation rates of global forest covers during the past decades, there is an ever-increasing need to monitor forest covers at both fine spatial and temporal resolutions. Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat series images have been used commonly for satellite-derived forest cover mapping. However, the spatial resolution of MODIS images and the temporal resolution of Landsat images are too coarse to observe forest cover at both fine spatial and temporal resolutions. In this paper, a novel multiscale spectral-spatial-temporal superresolution mapping (MSSTSRM) approach is proposed to update Landsat-based forest maps by integrating current MODIS images with the previous forest maps generated from Landsat image. Both the 240 m MODIS bands and 480 m MODIS bands were used as inputs of the spectral energy function of the MSSTSRM model. The principle of maximal spatial dependence was used as the spatial energy function to make the updated forest map spatially smooth. The temporal energy function was based on a multiscale spatial-temporal dependence model, and considers the land cover changes between the previous and current time. The novel MSSTSRM model was able to update Landsat-based forest maps more accurately, in terms of both visual and quantitative evaluation, than traditional pixel-based classification and the latest sub-pixel based super-resolution mapping methods The results demonstrate the great efficiency and potential of MSSTSRM for updating fine temporal resolution Landsat-based forest maps using MODIS images. 相似文献
15.
Optical Earth Observation data with moderate spatial resolutions, typically MODIS (Moderate Resolution Imaging Spectroradiometer), are of particular value to environmental applications due to their high temporal and spectral resolutions. Time-series of MODIS data capture dynamic phenomena of vegetation and its environment, and are considered as one of the most effective data sources for land cover mapping at a regional and national level. However, the time-series, multiple bands and their derivations such as NDVI constitute a large volume of data that poses a significant challenge for automated mapping of land cover while optimally utilizing the information it contains. In this study, time-series of 10-day cloud-free MODIS composites and its derivatives – NDVI and vegetation phenology information, are fully assessed to determine the optimal data sets for deriving land cover. Three groups of variable combinations of MODIS spectral information and its derived metrics are thoroughly explored to identify the optimal combinations for land cover identification using a data mining tool.The results, based on the assessment using time-series of MODIS data, show that in general using a longer time period of the time-series data and more spectral bands could lead to more accurate land cover identification than that of a shorter period of the time-series and fewer bands. However, we reveal that, with some optimal variable combinations of few bands and a shorter period of time-series data, the highest possible accuracy of land cover classification can be achieved. 相似文献
16.
《地理信息系统科学与遥感》2013,50(3):398-411
This study examines the relative utility of quad-polarization spaceborne radar and derived texture measures for classification of specific land cover categories at a site in east-central Sudan near the city of Wad Madani. Japanese Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) quad-polarization spaceborne radar data at 12.5 m spatial resolution were obtained for this study. Measures of variance texture were applied to the original PALSAR data over varied window sizes. Transformed divergence (TD) measures of separability were calculated in order to evaluate the best bands from the original and texture measures for classification. Results show that quad-polarization radar data and derived texture measures have high separability between different land cover classes, and therefore hold potential to attain high levels of classification accuracy. Specifically, when used individually the cross-polarization bands showed the highest separability, but when used in combination some mix of cross- and like-polarization bands had the highest separability. 相似文献
17.
18.
天宫一号高光谱成像仪具有空间分辨率高、光谱分辨率高、图谱合一等特性，在中国航天高光谱领域具有里程碑的意义。针对一般遥感场景分类数据集尺度单一、光谱分辨率较低等问题，本文提出基于天宫一号的多谱段、高空间分辨率、多时相高光谱遥感场景分类数据集(TG1HRSSC)。利用天宫一号高光谱成像仪获取的高质量数据，经过辐射校正、几何校正、空间裁剪、波段筛选、数据质量分析与控制等，制作了一批通用的航天高光谱遥感场景分类数据集，通过载人航天空间应用数据推广服务平台（http://www.msadc.cn [2019-09-10]）进行分发和共享。该数据集包括天宫一号高光谱成像仪获取的城镇、农田、林地、养殖塘、荒漠、湖泊、河流、港口、机场等9个典型地物场景的204个高光谱影像数据，其中5 m分辨率全色谱段1个波段、10 m分辨率可见近红外谱段54个有效波段以及20 m分辨率短波红外谱段52个有效波段。研究利用AlexNet、VGG-VD-16、GoogLeNet等深度学习算法网络对构建的数据集进行场景分类的试验，结果表明该数据集的场景分类应用实现较好效果。由于该数据集具备高分辨、高光谱等特征优势，未来在语义理解、多目标检测等方面有着广泛的应用价值。 相似文献
19.
Gustavo Antonio Piazza Alexander Christian Vibrans Veraldo Liesenberg Júlio Cesar Refosco 《地理信息系统科学与遥感》2016,53(2):206-226
Airborne high–spatial resolution images were evaluated for mapping purposes in a complex Atlantic rainforest environment in southern Brazil. Two study sites, covered predominantly by secondary evergreen rainforest, were surveyed by airborne multispectral high-resolution imagery. These aerophotogrammetric images were acquired at four spectral bands (visible to near-infrared) with spatial resolution of 0.39 m. We evaluated different data input scenarios to suit the object-oriented classification approach. In addition to the four spectral bands, auxiliary products such as band ratios and digital elevation models were considered. Comparisons with traditional pixel-based classifiers were also performed. The results showed that the object-based classification approach yielded a better overall accuracy, ranging from 89% to 91%, than the pixel-based classifications, which ranged from 62% to 63%. The individual classification accuracy of forest-related classes, such as young successional forest stages, benefits the object-based approach. These classes have been reported in the literature as the most difficult to map in tropical environments. The results confirm the potential of object-based classification for mapping procedures and discrimination of successional forest stages and other related land use and land cover classes in complex Atlantic rainforest environments. The methodology is suggested for further SAAPI acquisitions in order to monitor such endangered environment as well as to support National Land and Environmental Management Protocols. 相似文献
20.
利用决策树工具的土地利用类型遥感识别方法研究 总被引：3，自引：0，他引：3
应用决策树的理论和方法,利用遥感数据及其他相关数据和资料进行土地利用信息分类。通过研究地物光谱统计特征,讨论了通过耕地指数等归一化地类指数来增强影像地类特征、结合DEM提取土地利用信息的决策树分支点的设计方法,较好地解决了水体和建筑阴影、道路等容易混淆区域的区分问题。 相似文献