Sub-pixel mapping of remotely sensed imagery with hybrid intra- and inter-pixel dependence

Sub-pixel mapping of remotely sensed imagery is often performed by assuming that land cover is spatially dependent both within and between image pixels. Intra- and inter-pixel dependencies are two widely used approaches to represent different land-cover spatial dependencies at present. However, merely using intra- or inter-pixel dependence alone often fails to fully describe land-cover spatial dependence, making current sub-pixel mapping models defective. A more reasonable object for sub-pixel mapping is maximizing both intra- and inter-pixel dependencies simultaneously instead of using only one of them. In this article, the differences between intra- and inter-pixel dependencies are discussed theoretically, and a novel sub-pixel mapping model aiming to maximize hybrid intra- and inter-pixel dependence is proposed. In the proposed model, spatial dependence is formulated as a weighted sum of intra-pixel dependence and inter-pixel dependence to satisfy both intra- and inter-pixel dependencies. By application to artificial and synthetic images, the proposed model was evaluated both visually and quantitatively by comparing with three representative sub-pixel mapping algorithms: the pixel swapping algorithm, the sub-pixel/pixel attraction algorithm, and the pixel swapping initialized with sub-pixel/pixel attraction algorithm. The results showed increased accuracy of the proposed algorithm when compared with these traditional sub-pixel mapping algorithms.     

遥感影像亚像元制图方法研究进展综述

遥感影像混合像元的普遍存在给遥感影像解译造成困扰。有效处理混合像元问题,细化分类结果,获得更为精细的地物细节信息就需要进行亚像元绘图。目前亚像元制图方法主要包括3个步骤:① 混合像元分解;② 提取软信息;③ 亚像元制图。总结归纳了近年来遥感影像亚像元绘图领域的研究进展和成果,详细阐述了亚像元制图的步骤及涉及的研究方法。依据辅助信息的类型将亚像元绘图方法大致划分为:基于空间相关性、基于空间结构信息、基于神经网络、基于像元交换途径的4类亚像元分类方法,并分别对各种方法的优缺点进行了分析对比。最后,评述了亚像元制图的发展趋势。     

Soft-then-hard super-resolution mapping based on a spatial attraction model with multiscale sub-pixel shifted images

Super-resolution mapping (SRM) is a technique for exploring spatial distribution information of the land-cover classes at finer spatial resolution. The soft-then-hard super-resolution mapping (STHSRM) algorithm is a type of SRM algorithm that first estimates the soft class values for sub-pixels at the target fine spatial resolution and then predicts the hard class labels for sub-pixels. The sub-pixel shifted images from the same area can be incorporated to improve the accuracy of STHSRM algorithm. In this article, multiscale sub-pixel shifted images (MSSI) based on the fine-scale model and the coarse-scale model are utilized to increase the accuracy of STHSRM. First, class fraction images are derived from multiple sub-pixel shifted coarse spatial resolution images by soft classification. Then using the sub-pixel/sub-pixel spatial attraction model as fine-scale and the sub-pixel/pixel spatial attraction model as coarse scale, all MSSI can be derived from fraction images. The MSSI for each class are then integrated to obtain the desired fine spatial resolution images. Finally, the integrated fine spatial resolution images are used to allocate classes for sub-pixel. Experiments on two synthetic remote sensing images and a real hyperspectral remote sensing imagery show that the proposed method produces higher mapping accuracy result.     

A linearised pixel-swapping method for mapping rural linear land cover features from fine spatial resolution remotely sensed imagery

Accurate maps of rural linear land cover features, such as paths and hedgerows, would be useful to ecologists, conservation managers and land planning agencies. Such information might be used in a variety of applications (e.g., ecological, conservation and land management applications). Based on the phenomenon of spatial dependence, sub-pixel mapping techniques can be used to increase the spatial resolution of land cover maps produced from satellite sensor imagery and map such features with increased accuracy. Aerial photography with a spatial resolution of 0.25 m was acquired of the Christchurch area of Dorset, UK. The imagery was hard classified using a simple Mahalanobis distance classifier and the classification degraded to simulate land cover proportion images with spatial resolutions of 2.5 and 5 m. A simple pixel-swapping algorithm was then applied to each of the proportion images. Sub-pixels within pixels were swapped iteratively until the spatial correlation between neighbouring sub-pixels for the entire image was maximised. Visual inspection of the super-resolved output showed that prediction of the position and dimensions of hedgerows was comparable with the original imagery. The maps displayed an accuracy of 87%. To enhance the prediction of linear features within the super-resolved output, an anisotropic modelling component was added. The direction of the largest sums of proportions was calculated within a moving window at the pixel level. The orthogonal sum of proportions was used in estimating the anisotropy ratio. The direction and anisotropy ratio were then used to modify the pixel-swapping algorithm so as to increase the likelihood of creating linear features in the output map. The new linear pixel-swapping method led to an increase in the accuracy of mapping fine linear features of approximately 5% compared with the conventional pixel-swapping method.     

Super-resolution mapping using Hopfield Neural Network with panchromatic imagery

Land-cover proportions of mixed pixels can be predicted using soft classification. From the land-cover proportions, a hard land-cover map can be predicted at sub-pixel spatial resolution using super-resolution mapping techniques. It has been demonstrated that the Hopfield Neural Network (HNN) provides a suitable method for super-resolution mapping. To increase the detail and accuracy of the sub-pixel land-cover map, supplementary information at an intermediate spatial resolution can be used. In this research, panchromatic (PAN) imagery was used as an additional source of information for super-resolution mapping. Information from the PAN image was captured by a new PAN reflectance constraint in the energy function of the HNN. The value of the new PAN reflectance constraint was defined based on forward and inverse models with local end-member spectra and local convolution weighting factors. Two sets of simulated and degraded data were used to test the new technique. The results indicate that PAN imagery can be used as a source of supplementary information to increase the detail and accuracy of sub-pixel land-cover maps produced by super-resolution mapping from land-cover proportion images.     

基于局部连续性与全局相似性的光谱保持型亚像元映射

遥感图像的像元级分类精度受混合像元的影响. 亚像元映射以像元分解获得的丰度值为基础,在地物分布规律的约束下,细化估计各类地物的亚像元级分布模式. 本文同时考虑了地物分布的空间与光谱信息,提出了一种基于局部连续性与全局相似性的光谱保持型亚像元映射算法. 针对地物的空间分布特性,提出了利用类内离散度对局部连续性进行建模,并通过相似分布像元表示误差引入全局相似性约束项. 针对地物的光谱特性,采用最小化光谱误差约束了亚像元映射过程中的光谱无失真性. 模拟数据与真实数据上的实验结果表明,本文算法比其他同类算法具有更高的估计精度,且更适合于实际应用.     

基于单亲遗传算法和子像元/像元空间吸引模型的亚像元制图研究

混合像元普遍存在于遥感图像数据中。与传统的硬分类(Hard Classification)方法相比,在处理混合像元时,软分类(Soft Classification)技术可以避免信息丢失;但是,通过软分类技术获得的结果,仍然无法确定各分类在像元中的具体位置。子像元制图(或超分辨率制图、亚像元制图)技术能将软分类技术得到的结果转化为更高分辨率的图像,它能兼得软分类和硬分类两者的优势。将遗传算法的一个变种-单亲遗传算法应用于子像元制图,结合子像元/像元空间吸引模型,单亲遗传算法能直接获得子像元制图结果。以合成的图像和实际的土地覆盖图像为实验对象,通过目视比较和定量精度评价,与硬分类的结果相比,该方法能取得更高的制图精度和更好的结果。     

Sub-pixel water temperature estimation from thermal-infrared imagery using vectorized lake features

Water skin temperature derived from thermal infrared satellite data are used in a wide variety of studies. Many of these studies would benefit from frequent, high spatial resolution (100 m pixels) thermal imagery but currently, at any given location, such data are only available every few weeks from spaceborne sensors such as ASTER. Lower spatial resolution (1 km pixels) thermal imagery is available multiple times per day at any given location, from several sensors such as MODIS on board both the AQUA and TERRA satellite platforms. In order to fully exploit lower spatial resolution imagery, a sub-pixel unmixing technique has been developed and tested at Quesnel Lake, British Columbia, Canada. This approach produces accurate, frequent high spatial resolution water skin temperature maps by exploiting a priori knowledge of water boundaries derived from vectorized water features. The pixel water-fraction maps are then input to a gradient descent algorithm to solve the mixed pixel ground leaving radiance equation for sub-pixel water temperature. Ground-leaving radiance is estimated from standard temperature and emissivity data products for pure pixels and a simple regression technique to estimate atmospheric effects. In this test case, MODIS 1 km thermal imagery was used along with 1:50,000 water features to create a high-resolution (100 m) water skin temperature map. This map is compared to a concurrent ASTER temperature image and found to be within 1 °C of the ASTER skin temperature 99% of the time. This is a considerable improvement over the 2.55 °C difference between the original MODIS product and ASTER image due to land temperature contamination. The algorithm is simple, effective, and unlocks a largely untapped resource for limnological and hydrological studies.     

Sub-pixel vs. super-pixel-based greenspace mapping along the urban–rural gradient using high spatial resolution Gaofen-2 satellite imagery: a case study of Haidian District,Beijing, China

Greenspace in urban areas is closely related to urban ecosystems, economy, culture, and society. Recently, rapid urban development and expansion are always dominated by a series of human–environment interactions, which can lead to various spatial patterns of urban greenspace especially along the urban–rural gradient. Urban–rural greenspace mapping is therefore of great importance to provide a comprehensive insight for urban planners and managers. In our study, we adopted both the sub-pixel and super-pixel strategies to map the greenspace in Haidian District, Beijing, China. Specifically, the fully constrained linear spectral unmixing and object-based classification methods were implemented as the representatives of sub-pixel and super-pixel strategies, respectively. The high spatial resolution Gaofen-2 multispectral imagery collected in September, 2015 was used in this study. The results showed that the overall accuracies of greenspace mapping by the super-pixel method were higher than those by the sub-pixel method in the selected dense urban, sub-urban, and rural subsets. Obviously, the super-pixel method was more advantageous for mapping greenspace from the high spatial resolution imagery, especially for patches of greenspace in rural and mountain areas. When further comparing these two methods using the medium spatial resolution Landsat-8 imagery, we concluded that the sub-pixel method failed to keep the same levels of greenspace mapping accuracies as those using the high spatial resolution Gaofen-2 imagery but outperformed the super-pixel method especially in the dense urban and sub-urban subsets due to their high degrees of greenspace fragmentation. Furthermore, the sub-pixel method also demonstrated its merits in terms of automation and operability compared to the super-pixel method.     

Sub-pixel Mapping with Partheno-Genetic Algorithm and Sub-pixel/pixel Spatial Attraction Model

Mixed pixels are widely presented in remotely sensed images.Soft classification techniques can avoid the loss of information comparing to hard classification methods while handling mixed pixels.However,the assignment to these classes by soft classification does not specify the location in the pixel.Sub-pixel mapping (or super-resolution mapping) is a technique which designed to use the information obtained by soft classification to get a sharpened image and it can incorporate benefits of both hard and soft classification techniques.In this paper,a variation of genetic algorithm,named as partheno-genetic algorithm (PGA),is developed to accomplish the sub\|pixel mapping.With the sub-pixel/pixel attraction model,PGA can achieve sub-pixel mapping in a straightforward one-pass process.It is evaluated with artificial and degraded land cover images by visual and quantitative classification accuracy indices.The results show this method can increase accuracy while compared to hard classification.     

地球观测1号高光谱与全色图像融合的最佳方法

受制于成像原理及制造技术等因素,航天高光谱遥感图像的空间分辨率相对较低,为此提出将高光谱图像与高空间分辨率图像进行融合处理,设计最佳的增强高光谱遥感图像空间分辨率的融合算法。针对地球观测1号(EO-1)Hyperion高光谱图像和高级陆地成像仪（ALI）全色波段图像的特点,从9种具体遥感图像融合算法中选用4种融合算法开展山区与城市的数据融合实验,即Gram-Schmidt光谱锐化融合法、平滑调节滤波(SFIM)变换融合法、加权平均法（WAM）融合法和小波变换（WT）融合法,并分别从定性、定量和分类精度三方面对这些方法的融合效果进行综合评价与对比分析,从而确定适合EO-1高光谱与全色图像融合的最佳方法。实验结果显示：从图像融合效果看,在所采用的4种融合方法中,Gram-Schmidt光谱锐化融合法的效果最好;从图像分类效果看,基于融合图像的分类效果要优于基于源图像的分类效果。理论分析与实验结果均表明：Gram-Schmidt光谱锐化融合法是一种较为理想的高光谱与高空间分辨率遥感图像的融合算法,为提高高光谱遥感图像的清晰度、可靠性及图像的地物识别和分类的准确性提供有力的支持。     

Combining medium and coarse spatial resolution satellite data to improve the estimation of sub-pixel NDVI time series

The potential of multitemporal coarse spatial resolution remotely sensed images for vegetation monitoring is reduced in fragmented landscapes, where most of the pixels are composed of a mixture of different surfaces. Several approaches have been proposed for the estimation of reflectance or NDVI values of the different land-cover classes included in a low resolution mixed pixel. In this paper, we propose a novel approach for the estimation of sub-pixel NDVI values from multitemporal coarse resolution satellite data. Sub-pixel NDVIs for the different land-cover classes are calculated by solving a weighted linear system of equations for each pixel of a coarse resolution image, exploiting information about within-pixel fractional cover derived from a high resolution land-use map. The weights assigned to the different pixels of the image for the estimation of sub-pixel NDVIs of a target pixel i are calculated taking into account both the spatial distance between each pixel and the target and their spectral dissimilarity estimated on medium-resolution remote-sensing images acquired in different periods of the year. The algorithm was applied to daily and 16-day composite MODIS NDVI images, using Landsat-5 TM images for calculation of weights and accuracy evaluation.Results showed that application of the algorithm provided good estimates of sub-pixel NDVIs even for poorly represented land-cover classes (i.e., with a low total cover in the test area). No significant accuracy differences were found between results obtained on daily and composite MODIS images. The main advantage of the proposed technique with respect to others is that the inclusion of the spectral term in weight calculation allows an accurate estimate of sub-pixel NDVI time series even for land-cover classes characterized by large and rapid spatial variations in their spectral properties.     

Image interpolation using MLP neural network with phase compensation of wavelet coefficients

When interpolating images in the wavelet domain, the main problem is how to estimate the finest detail coefficients. Wavelet coefficients across scales have an interscale dependency, and the dependency varies according to the local energy of the coefficients. This implies the possible existence of functional mappings from one scale to another scale. If we can estimate the mapping parameters from the observed coefficients, then it is possible to predict the finest detail coefficients. In this article, we use the multilayer perceptron (MLP) neural networks to learn a mapping from the coarser scale to the finer scale. When exploiting the MLP neural networks, phase uncertainty, a well-known drawback of wavelet transforms, makes it difficult for the networks to learn the interscale mapping. We solve this location ambiguity by using a phase-shifting filter. After the single-level phase compensation, a wavelet coefficient vector is assigned to one of the energy-dependent classes. Each class has its corresponding network. In the simulation results, we show that the proposed scheme outperforms the previous wavelet-domain interpolation method as well as the conventional spatial domain methods.     

Mapping sub-pixel proportional land cover with AVHRR imagery

A problem with NOAA AVHRR imagery is that the intrinsic scale of spatial variation in land cover in the U.K. is usually finer than the scale of sampling imposed by the image pixels. The result is that most NOAA AVHRR pixels contain a mixture of land cover types (sub-pixel mixing). Three techniques for mapping the sub-pixel proportions of land cover classes in the New Forest, U.K. were compared: (i) artificial neural networks (ANN); (ii) mixture modelling; and (iii) fuzzy c -means classification. NOAA AVHRR imagery and SPOT HRV imagery, both for 28 June 1994, were obtained. The SPOT HRV images were classified using the maximum likelihood method, and used to derive the 'known' sub-pixel proportions of each land cover class for each NOAA AVHRR pixel. These data were then used to evaluate the predictions made (using the three techniques and the NOAA AVHRR imagery) in terms of the amount of information provided, the accuracy with which that information is provided, and the ease of implementation. The ANN was the most accurate technique, but its successful implementation depended on accurate co-registration and the availability of a training data set. Supervised fuzzy c -means classification was slightly more accurate than mixture modelling.     

Super-resolution land-cover mapping using multiple sub-pixel shifted remotely sensed images

Super-resolution land-cover mapping is a promising technology for prediction of the spatial distribution of each land-cover class at the sub-pixel scale. This distribution is often determined based on the principle of spatial dependence and from land-cover fraction images derived with soft classification technology. However, the resulting super-resolution land-cover maps often have uncertainty as no information about sub-pixel land-cover patterns within the low-resolution pixels is used in the model. Accuracy can be improved by incorporating supplemental datasets to provide more land-cover information at the sub-pixel scale; but the effectiveness of this is limited by the availability and quality of these additional datasets. In this paper, a novel super-resolution land-cover mapping technology is proposed, which uses multiple sub-pixel shifted remotely sensed images taken by observation satellites. These satellites take images over the same area once every several days, but the images are not identical because of slight orbit translations. Low-resolution pixels in these remotely sensed images therefore contain different land-cover fractions that can provide useful information for super-resolution land-cover mapping. We have constructed a Hopfield Neural Network (HNN) model to solve it. Maximum spatial dependence is the goal of the proposed model, and the fraction maps of all images are constraints added to the energy function of HNN. The model was applied to synthetic artificial images as well as to a real degraded QuickBird image. The output maps derived from different numbers of images at different zoom factors were compared visually and quantitatively to the super-resolution map generated from a single image. The resulting land-cover maps with multiple remotely sensed images were more accurate than was the single image map. The use of multiple remotely sensed images is therefore a promising method for decreasing the uncertainty of super-resolution land-cover mapping. Moreover, remotely sensed images with similar spatial resolution from different satellite platforms can be used together, allowing a fusion of information obtained from remotely sensed imagery.     

两种基于空间相关性的遥感亚像元分类制图方法对比分析

为了对比基于Hopfield Neural Network(HNN)和几何绘图的遥感亚像元分类制图方法的具体性能,验证空间相关性原理用于遥感亚像元定位的可行性。以一个研究区的TM影像为对象,通过利用HNN和几何亚像元制图方法,获得该区的亚像元定位结果,对比分析了各方法的视觉效果、精度和时间复杂度。结果表明:空间相关性特性在两种方法中得到了良好的体现,为后续亚像元制图研究应用提供参考。     

结合超分辨率重建的神经网络亚像元定位方法

遥感影像中普遍存在着混合像元,如何分析和解译混合像元一直是人们研究的热点。亚像元定位方法是将混合像元分解成为亚像元,并赋予不同的端元组分,以提高影像整体分类精度的一种技术。本文在神经网络亚像元定位模型的基础上,结合超分辨率重建理论,提出一种新型的BPMAP模型,在每一个类别的组成分图像与亚像元定位图像之间建立起高、低分辨率的观测模型,采用最大后验估计（MAP）算法对BP神经网络的定位结果进行约束,最终确定混合像元内部各组分合适的空间位置。通过对模拟的简单图像和长江三峡地区的ETM影像进行实验,结果表明,与神经网络模型相比,本文方法能够更加有效地解决亚像元定位的问题,进一步消除定位过程中产生的误差,提高精度。     

一种新颖的医学图像锐化增强算法

针对医学图像组织间不明显现象,提出了一种基于模糊规则和小波变换的医学图像锐化增强算法。对不同尺度的小波系数进行锐化增强时,首先根据该尺度低频系数中心像素与其邻域像素的相容性利用模糊规则自适应计算非线性细节增益系数。然后把增益系数与细节小波系数相乘,小波重建后得到增强图像。实验结果表明,提出的算法对图像细节进行增强的同时能够有效地抑制噪声。     

Wavelet-based image interpolation using multilayer perceptrons

Changing the resolution of digital images and video is needed image processing systems. In this paper, we present nonlinear interpolation schemes for still image resolution enhancement. The proposed neural network interpolation method is based on wavelet reconstruction. With the wavelet decomposition, the image signals can be divided into several time–frequency portions. In this work, the wavelet decomposition signal is used to train the neural networks. The pixels in the low-resolution image are used as the input signal of the neural network to estimate all the wavelet sub-images of the corresponding high-resolution image. The image of increased resolution is finally produced by the synthesis procedure of wavelet transform. In the simulation, the proposed method obtains much better performance than other traditional methods. Moreover, the easy implementation and high flexibility of the proposed algorithm also make it applicable to various other related problems.     

一种自适应的基于局部小波系数特征的遥感图像融合方法

光谱保持和高分辨率保留是影像融合的两个重要问题。本文提出了一种自适应的基于局部小波系数特征的遥感影像融合方法。该方法在对多光谱影像进行IHS变换的基础上,对多光谱的I分量和高分辨率的全色影像分别进行小波多分辨率分析,而后对分解得到的近似分量以及各层各方向的细节分量利用移动模板逐一提取对应的小波系数矩阵的局部特征,采用本文提出的自适应融合准则在小波域进行影像融合,最后通过小波逆变换得到新的I′分量,与H,S分量一起还原到RGB空间,最终得到融合后的高分辨率多光谱彩色图像。本文采用一组TM多光谱图像和SPOT全色图像数据进行融合实验,利用标准差、熵,光谱扭曲度等5个重要评价指标对融合效果进行数理分析。其实验融合图像的目视效果和统计指标均优于IHS融和方法和小波融合方法。