运用GVF Snake算法提取水域的不规则边界

GVF Snake是一种改进型主动轮廓提取算法。本文在详细介绍GVF Snake原理的基础上,重点对GVF Snake的内、外部约束力在边界提取中的作用以及初始边界对提取结果的影响进行了实验研究,提出了初始边界和内部约束力权值的合理设置方法,设计并实现了交互式GVF Snake算法,并用于提取遥感影像上水域的不规则边界。该算法采用种子点区域生长法自动给出水域的初始边界,采用人机交互法设置内部约束力权值,然后运用GVF Snake算法搜索水域的实际边界。实验表明：对于形状极不规则的水域,交互式GVF Snake算法也能方便、快速、准确地获取其边界。     

Towards 3D map generation from digital aerial images

This paper describes the fusion of information extracted from multispectral digital aerial images for highly automatic 3D map generation. The proposed approach integrates spectral classification and 3D reconstruction techniques. The multispectral digital aerial images consist of a high resolution panchromatic channel as well as lower resolution RGB and near infrared (NIR) channels and form the basis for information extraction.Our land use classification is a 2-step approach that uses RGB and NIR images for an initial classification and the panchromatic images as well as a digital surface model (DSM) for a refined classification. The DSM is generated from the high resolution panchromatic images of a specific photo mission. Based on the aerial triangulation using area and feature-based points of interest the algorithms are able to generate a dense DSM by a dense image matching procedure. Afterwards a true ortho image for classification, panchromatic or color input images can be computed.In a last step specific layers for buildings and vegetation are generated and the classification is updated.     

Using FCMC, FVS, and PCA techniques for feature extraction of multispectral images

In this letter, a new nonlinear approach based on a combination of the fuzzy c-means clustering (FCMC), feature vector selection and principal component analysis (PCA) is proposed to extract features of multispectral images when a very large number of samples need to be processed. The main contribution of this letter is to provide a preprocessing method for classifying these images with higher accuracy compared to the single PCA and kernel PCA. Finally, some experimental results demonstrate that our proposed approach is effective and efficient in analyzing multispectral images.     

Spectral and Spatial Quality Analysis in Pan Sharpening Process

Image fusion is a process to obtain new images containing more information by combining images obtained same or different sensors. With most of the earth observation satellites, high spatial resolution panchromatic images and low spatial resolution multispectral images are obtained. As an example of image fusion ??pan sharpening?? is a process of combining of high spatial resolution panchromatic images and low spatial resolution multispectral images. At the end of the fusion process both high spatial and spectral resolution new images are obtained. In this study, panchromatic and multispectral images gathered from Ikonos were used. Panchromatic and multispectral images belonging to the same sensor were combined by using different image fusion methods. As pan sharpening methods Brovey transform, Modified IHS, Principal Component Analysis (PCA), Wavelet PC transform and Wavelet A Trous transformation methods were used. Quality of fused products was evaluated from the point of view of both visual and statistical criteria. While wavelet based methods are succesfull in terms of protection of spectral quality of original multispectral images, the colorbased and statistical methods are giving better results within the improvement of spatial content.     

保持光谱信息的遥感图像融合方法研究

常用的遥感图像融合方法,如IHS变换法、Brovey变换法和主成分变换法等在实施图像融合时,均会有不同程度的光谱扭曲现象.探讨能有效保持光谱信息的EECN融合法.EECN融合法采用比值变换法,同时对参与融合的全色波段进行增强边缘,融合后的图像在光谱保持性能、分类精度等方面均较优.     

基于MRF随机场和广义混合模型的遥感图像分级聚类

有限混合模型FM的分级聚类已广泛应用于不同领域,然而,它的计算复杂度与观测数据的平方成正比,因此,在海量数据方面的应用就受到了限制。另一方面,多光谱图像数据中同时包含有空间和光谱两类信息,但大多数基于像素的多光谱图像聚类方法,仅使用了其频谱信息而忽视了空间信息。本文提出了一种新的基于广义有限混合模型GFM的分级聚类方法,该算法把MRF随机场和GFM模型结合在一起,分类数可以通过PLIC准则自动确定。算法在执行过程中,采用K均值聚类方式获得过分类图像,分级聚类从过分类图像开始,代替原来从单点类开始的方式,这样可以方便获取GFM模型成分密度的初始参数。最后,采用由Gibbs采样器生成的仿真测试图对算法的精度进行了定量评价,通过与K均值聚类和FM聚类的比较说明了本文算法的优越性,同时用荷兰Flevoland农业地区的极化SAR图像验证了本文算法的有效性。     

Combined use of LiDAR data and multispectral earth observation imagery for wetland habitat mapping

Although wetlands play a key role in controlling flooding and nonpoint source pollution, sequestering carbon and providing an abundance of ecological services, the inventory and characterization of wetland habitats are most often limited to small areas. This explains why the understanding of their ecological functioning is still insufficient for a reliable functional assessment on areas larger than a few hectares. While LiDAR data and multispectral Earth Observation (EO) images are often used separately to map wetland habitats, their combined use is currently being assessed for different habitat types. The aim of this study is to evaluate the combination of multispectral and multiseasonal imagery and LiDAR data to precisely map the distribution of wetland habitats. The image classification was performed combining an object-based approach and decision-tree modeling. Four multispectral images with high (SPOT-5) and very high spatial resolution (Quickbird, KOMPSAT-2, aerial photographs) were classified separately. Another classification was then applied integrating summer and winter multispectral image data and three layers derived from LiDAR data: vegetation height, microtopography and intensity return. The comparison of classification results shows that some habitats are better identified on the winter image and others on the summer image (overall accuracies = 58.5 and 57.6%). They also point out that classification accuracy is highly improved (overall accuracy = 86.5%) when combining LiDAR data and multispectral images. Moreover, this study highlights the advantage of integrating vegetation height, microtopography and intensity parameters in the classification process. This article demonstrates that information provided by the synergetic use of multispectral images and LiDAR data can help in wetland functional assessment     

广义马尔可夫随机场及其在多光谱纹理影像分类中的应用

在二维马尔可夫随机场模型的基础上，提出顾及波段间的空间相关性，发展了一种适用于多光谱纹理影像分类的广义马尔可夫随机场模型。鉴于广义马尔可夫随机场模型的复杂性，利用最大伪似然法建立了求解模型参数的简化方程式，实现了纹理特征的快速提取。结合提取的纹理特征影像和光谱特征影像，采用概率松弛算法实现影像的分类。实验证明，提出的基于广义马尔可夫随机场的多光谱纹理影像分类算法克服了传统的基于光谱特征的分类算法的局限性，提高了纹理影像的分类精度。     

Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data

Wetland ecosystems have experienced dramatic challenges in the past few decades due to natural and human factors. Wetland maps are essential for the conservation and management of terrestrial ecosystems. This study is to obtain an accurate wetland map using an object-based stacked generalization (Stacking) method on the basis of multi-temporal Sentinel-1 and Sentinel-2 data. Firstly, the Robust Adaptive Spatial Temporal Fusion Model (RASTFM) is used to get time series Sentinel-2 NDVI, from which the vegetation phenology variables are derived by the threshold method. Subsequently, both vertical transmit-vertical receive (VV) and vertical transmit-horizontal receive (VH) polarization backscatters (σ0 VV, σ0 VH) are obtained using the time series Sentinel-1 images. Speckle noise inherent in SAR data, resulting in over-segmentation or under-segmentation, can affect image segmentation and degrade the accuracies of wetland classification. Therefore, we segment Sentinel-2 multispectral images to delineate meaningful objects in this study. Then, in order to reduce data redundancy and computation time, we analyze the optimal feature combination using the Sentinel-2 multispectral images, Sentinel-2 NDVI time series, phenological variables and other vegetation index derived from Sentinel-2 multispectral images, as well as time series Sentinel-1 backscatters at the object level. Finally, the stacked generalization algorithm is utilized to extract the wetland information based on the optimal feature combination in the Dongting Lake wetland. The overall accuracy and Kappa coefficient of the object-based stacked generalization method are 92.46% and 0.92, which are 3.88% and 0.04 higher than that using the pixel-based method. Moreover, the object-based stacked generalization algorithm is superior to single classifiers in classifying vegetation of high heterogeneity areas.     

深度残差网络的多光谱遥感图像显著目标检测

本文侧重于介绍智能化摄影测量深度学习的深度残差方法。显著目标检测致力于自动检测和定位图像中人最感兴趣的目标区域。多波段遥感图像因其更加丰富的光谱信息和揭示观测目标物理属性的能力在目标检测中获得重要应用。传统的显著目标检测方法通过手工设计特征,计算图像各像素或者超像素与邻域像素或者超像素之间的对比度检测显著目标。随着深度学习的巨大发展,特别是全卷积神经网络的引入,基于深度卷积网络的显著目标检测算法取得重要进步。然而,由于数据获取和标记的困难,多波段遥感图像显著目标检测的研究依然主要采用手工设计特征。本文研究基于深度卷积神经网络的多波段遥感图像显著目标检测算法,提出一种基于深度残差网络的自上而下的多光波段遥感图像显著目标检测网络,该网络可以有效挖掘深度残差网络不同层次上的显著性特征,以端对端方式实现显著目标检测。为了应对多波段遥感图像数据量有限、无法训练深度残差网络的问题,本文提出通过浅层神经网络从RGB图像直接生成多波段遥感图像,实现光谱方向的超分辨率。在现有多波段遥感图像和可见光图像显著目标检测数据集上的试验结果超过当前最好方法10%以上,验证了本文方法的有效性。     

Automated geometric correction of multispectral images from High Resolution CCD Camera (HRCC) on-board CBERS-2 and CBERS-2B

China–Brazil Earth Resource Satellite (CBERS) imagery is identified as one of the potential data sources for monitoring Earth surface dynamics in the event of a Landsat data gap. Currently available multispectral images from the High Resolution CCD (Charge Coupled Device) Camera (HRCC) on-board CBERS satellites (CBERS-2 and CBERS-2B) are not precisely geo-referenced and orthorectified. The geometric accuracy of the HRCC multispectral image product is found to be within 2–11 km. The use of CBERS-HRCC multispectral images to monitor Earth surface dynamics therefore necessitates accurate geometric correction of these images. This paper presents an automated method for geo-referencing and orthorectifying the multispectral images from the HRCC imager on-board CBERS satellites. Landsat Thematic Mapper (TM) Level 1T (L1T) imagery provided by the U.S. Geological Survey (USGS) is employed as reference for geometric correction. The proposed method introduces geometric distortions in the reference image prior to registering it with the CBERS-HRCC image. The performance of the geometric correction method was quantitatively evaluated using a total of 100 images acquired over the Andes Mountains and the Amazon rainforest, two areas in South America representing vastly different landscapes. The geometrically corrected HRCC images have an average geometric accuracy of 17.04 m (CBERS-2) and 16.34 m (CBERS-2B). While the applicability of the method for attaining sub-pixel geometric accuracy is demonstrated here using selected images, it has potential for accurate geometric correction of the entire archive of CBERS-HRCC multispectral images.     

Improving classification accuracy of spectrally similar land covers in the rangeland and plateau areas with a combination of WorldView-2 and UAV images

This study aims to increase the accuracy of the object based classification approach to differentiate the spectrally similar land cover types to create thematic maps depicting the current land use status in rangeland. Firstly, the multispectral and panchromatic bands of a WorldView-2 MS and Pan images are fused. The fused WV-2 image is then classified with object based approach using Support Vector Machines (SVMs) classifier (Method 1). The overall classification accuracy for Method 1 is found to be 88.6%. Secondly, UAV ortho-image is utilised for segmentation process, which is required for the object based SVM classification of the WV-2 MS image (Method 2). The overall classification accuracy for Method 2 is obtained as 92.4%. It is realised that the Method 2 increases the object based classification accuracy by 4%, compared to Method 1. This result reveals that the object based classification of the UAV and WV-2 MS images makes significant contribution to the classification accuracy.     

基于MRF随机场的多光谱遥感影像最优化分级聚类

有限混合模型FM的分级聚类已广泛应用于不同领域,然而,由于它的计算复杂度与观测数据量平方成正比,致使在遥感影像方面应用受到了限制。另外,多光谱图像能提供空间和光谱两类信息详细的数据,但是,大多数多光谱图像聚类方法是基于像素的聚类,仅使用了其光谱信息而忽视了空间信息。本文定义一个相对混合密度函数,通过引入一个q-参数来调节各成分密度对其混合分布的贡献,提出一种广义有限混合模型GFM．设计一种新的适用于多光谱遥感影像的GFM分级聚类算法。该算法把MRF随机场和GFM模型结合在了一起,分类数通过PLIC准则自动确定。最后,利用仿真结果验证该算法的有效性,同时通过与K均值聚类、FM分级聚类以及SVMM分级聚类的比较说明本文算法的优越性。     

决策级融合的多分辨率遥感影像变化检测

针对多时相、多分辨率遥感影像数据的特点,充分考虑不同分辨率数据和不同变化检测应用的需求,将由粗到精数据集分层检测和决策级融合的思想引入到变化检测,以多时相多分辨率ALOS遥感影像为例,构建并试验了由粗到精变化检测的技术流程.该方法将ALOS多光谱数据视为粗数据集,将全色数据和融合数据视为精数据集,通过对3种数据集变化检...     

基于地统计学的图像纹理在岩性分类中的应用

纹理是遥感图像的重要特征,它揭示了图像中辐射亮度值空间变化的重要信息。本文运用地统计学中的对数变差函数计算图像纹理,并与图像的光谱信息结合,进行图像岩性分类,分析了不同大小窗口纹理信息对分类精度的影响。结果表明,运用地统计学原理进行图像分类,可大大提高图像的分类精度;采用较大窗口提取的纹理信息参与分类能使总体分类精度提高,但某些岩性类的分类精度有所下降,建议在实际应用中,根据具体情况选择窗口的大小。     

A Combined Detail Enhancing Algorithm and Texture Feature Extraction Method for Supervised Classification of Remote Sensing Images

In this paper, we propose a supervised classification in multispectral satellite images based on a novel detail enhancing texture feature extraction algorithm. The multispectral training and test images are first given for pre-processing, which is decomposed into low-pass approximation and high-pass multi-directional subbands by wavelet based contourlet transform. High pass subbands are easily interfered by noise. Based upon the Normal Shrink technique, thresholding is applied in high frequency images to eliminate the noise. The intra and inter scale fusion rule is used to combine the approximation and detail subbands to form the enhanced image. The co-occurrence features are calculated by forming the gray level co-occurrence matrix on training and test images. Mahalanobis distance classifier is applied on the training and test data sets for effective classification. The experiment result shows that the overall accuracy is improved to 2.2% for (Test-1) 2% for (Test-2) and 3.2 5% for (Test-3) and kappa coefficient is improved to 0.02 for (Test-1) image 0.03 for (Test-2) image and 0.03 (Test-3) image.     

联合IHS 变换和MAP 估计的遥感图像融合

为了提高多光谱图像和全色图像的融合质量, 提出一种基于推广的IHS(Generalized Intensity-Hue-Saturation, GIHS)变换与最大后验概率MAP(Maximum a Posteriori)相结合的遥感图像融合算法。该算法首先经过GIHS 变换, 由多光谱图像得到强度分量; 其次针对强度分量和全色图像, 通过MAP 构建高分辨率图像的成像模型, 采用最速下 降优化算法得到富含光谱信息的高分辨率全色图像; 进而依据GIHS 变换得到融合图像。实验中分别以IKONOS 卫 星、Quickbird 卫星的多光谱图像和全色图像为例, 进行融合算法验证, 并与GIHS 融合算法、传统的小波变换融合 算法、小波变换结合IHS 变换的融合算法等进行比较分析, 实验表明, 新的融合方法具有更好的融合效果。     

基于分辨率退化模型的全色和多光谱遥感影像融合方法

从影像成像的频率特性出发，提出了一种影像分辨率退化模型，并在此基础上提出了一种新的全色和多光谱遥感影像融合方法。