An iterative technique for the detection of land-cover transitionsin multitemporal remote-sensing images

The authors propose a supervised nonparametric technique based on the “compound classification rule” for minimum error, to detect land-cover transitions between two remote-sensing images acquired at different times. Thanks to a simplifying hypothesis, the compound classification rule is transformed into a form easier to compute. In the obtained rule, an important role is played by the probabilities of transitions, which take into account the temporal dependence between two images. In order to avoid requiring that training sets be representative of all possible types of transitions, the authors propose an iterative algorithm which allows the probabilities of transitions to be estimated directly from the images under investigation. Experimental results on two Thematic Mapper images confirm that the proposed algorithm may provide remarkably better detection accuracy than the “Post Classification Comparison” algorithm, which is based on the separate classifications of the two images     

A BISDN customer access architecture optimized in relation to network implementation technology

This paper aims at identifying an architecture model for a fibre-optic-based customer access network optimized at the minimum cost for the implementation technology and passive components inserted between the distribution centre and the subscriber premises. The optimization has been carried out on the basis of technical and economic considerations by taking into account the technology and market trends foreseen in this field. Moreover, a prediction of the cost reduction trend in the short-and medium-term scenario (up to 1995) has been derived for both the various passive components and the overall network implementation costs.     

Combining Laplacian images of different spatial frequencies(scales): implications for remote sensing image analysis

The author proposes a solution to the longstanding problem of how to combine the different scales of analysis in multifrequency image analysis. The premise for combining different scales of analysis is that the absolute value of the result of the difference of two Gaussian filters (DOG) will be at a maximum at different parts of an object for the DOGS passing the spatial frequencies composing those parts. Combining images derived from a DOGS passing a range of frequencies (called Laplacian images or the Laplacian pyramid) is performed by taking the maximum absolute value among the values in the Laplacian image being combined (for each pixel) to form what is called a multifrequency Laplacian image. The rationale for the development of a multifrequency Laplacian pyramid and its implications for multifrequency image analysis and remote-sensing image classification are discussed     

An advanced system for the automatic classification of multitemporal SAR images

A novel system for the classification of multitemporal synthetic aperture radar (SAR) images is presented. It has been developed by integrating an analysis of the multitemporal SAR signal physics with a pattern recognition approach. The system is made up of a feature-extraction module and a neural-network classifier, as well as a set of standard preprocessing procedures. The feature-extraction module derives a set of features from a series of multitemporal SAR images. These features are based on the concepts of long-term coherence and backscattering temporal variability and have been defined according to an analysis of the multitemporal SAR signal behavior in the presence of different land-cover classes. The neural-network classifier (which is based on a radial basis function neural architecture) properly exploits the multitemporal features for producing accurate land-cover maps. Thanks to the effectiveness of the extracted features, the number of measures that can be provided as input to the classifier is significantly smaller than the number of available multitemporal images. This reduces the complexity of the neural architecture (and consequently increases the generalization capabilities of the classifier) and relaxes the requirements relating to the number of training patterns to be used for classifier learning. Experimental results (obtained on a multitemporal series of European Remote Sensing 1 satellite SAR images) confirm the effectiveness of the proposed system, which exhibits both high classification accuracy and good stability versus parameter settings. These results also point out that properly integrating a pattern recognition procedure (based on machine learning) with an accurate feature extraction phase (based on the SAR sensor physics understanding) represents an effective approach to SAR data analysis.     

Comparison of different methods of classification in subband codingof images

This paper investigates various classification techniques, applied to subband coding of images, as a way of exploiting the nonstationary nature of image subbands. The advantages of subband classification are characterized in a rate-distortion framework in terms of "classification gain" and overall "subband classification gain." Two algorithms, maximum classification gain and equal mean-normalized standard deviation classification, which allow unequal number of blocks in each class, are presented. The dependence between the classification maps from different subbands is exploited either directly while encoding the classification maps or indirectly by constraining the classification maps. The trade-off between the classification gain and the amount of side information is explored. Coding results for a subband image coder based on classification are presented. The simulation results demonstrate the value of classification in subband coding.     

Low-complexity compression of multispectral images based on classified transform coding

Compression of remote-sensing images can be necessary in various stages of the image life, and especially on-board a satellite before transmission to the ground station. Although on-board CPU power is quite limited, it is now possible to implement sophisticated real-time compression techniques, provided that complexity constraints are taken into account at design time. In this paper we consider the class-based multispectral image coder originally proposed in [Gelli and Poggi, Compression of multispectral images by spectral classification and transform coding, IEEE Trans. Image Process. (April 1999) 476–489 [5]] and modify it to allow its use in real time with limited hardware resources. Experiments carried out on several multispectral images show that the resulting unsupervised coder has a fully acceptable complexity, and a rate–distortion performance which is superior to that of the original supervised coder, and comparable to that of the best coders known in the literature.     

Spectral-spatial classification of hyperspectral data based on a stochastic minimum spanning forest approach

In this paper, a new method for supervised hyperspectral data classification is proposed. In particular, the notion of stochastic minimum spanning forest (MSF) is introduced. For a given hyperspectral image, a pixelwise classification is first performed. From this classification map, M marker maps are generated by randomly selecting pixels and labeling them as markers for the construction of MSFs. The next step consists in building an MSF from each of the M marker maps. Finally, all the M realizations are aggregated with a maximum vote decision rule in order to build the final classification map. The proposed method is tested on three different data sets of hyperspectral airborne images with different resolutions and contexts. The influences of the number of markers and of the number of realizations M on the results are investigated in experiments. The performance of the proposed method is compared to several classification techniques (both pixelwise and spectral-spatial) using standard quantitative criteria and visual qualitative evaluation.     

COMPARE: classification of morphological patterns using adaptive regional elements

This paper presents a method for classification of structural brain magnetic resonance (MR) images, by using a combination of deformation-based morphometry and machine learning methods. A morphological representation of the anatomy of interest is first obtained using a high-dimensional mass-preserving template warping method, which results in tissue density maps that constitute local tissue volumetric measurements. Regions that display strong correlations between tissue volume and classification (clinical) variables are extracted using a watershed segmentation algorithm, taking into account the regional smoothness of the correlation map which is estimated by a cross-validation strategy to achieve robustness to outliers. A volume increment algorithm is then applied to these regions to extract regional volumetric features, from which a feature selection technique using support vector machine (SVM)-based criteria is used to select the most discriminative features, according to their effect on the upper bound of the leave-one-out generalization error. Finally, SVM-based classification is applied using the best set of features, and it is tested using a leave-one-out cross-validation strategy. The results on MR brain images of healthy controls and schizophrenia patients demonstrate not only high classification accuracy (91.8% for female subjects and 90.8% for male subjects), but also good stability with respect to the number of features selected and the size of SVM kernel used.     

Development of a technique to assess snow-cover mapping errors fromspace

Following the December 18, 1999, launch of the Earth Observing System (EOS) Terra satellite, daily snow-cover mapping is performed automatically at a spatial resolution of 500 m, cloud-cover permitting, using moderate resolution imaging spectroradiometer (MODIS) data. This paper describes a technique for calculating global-scale snow mapping errors and provides estimates of Northern Hemisphere snow mapping errors based on prototype MODIS snow mapping algorithms. Field studies demonstrate that under cloud-free conditions, when snow cover is complete, snow mapping errors are small (<1%) in all land covers studied except forests, where errors are often greater and more variable. Thus, the accuracy of Northern Hemisphere snow-cover maps is largely determined by percent of forest cover north of the snowline. From the 17-class International Geosphere-Biosphere Program (IGBP) land-cover maps of North America and Eurasia, the authors classify the Northern Hemisphere into seven land-cover classes and water. Estimated snow mapping errors in each of the land-cover classes are extrapolated to the entire Northern Hemisphere for areas north of the average continental snowline for each month. The resulting average monthly errors are expected to vary, ranging from about 5-10%, with the larger errors occurring during the months when snow covers the boreal forest in the Northern Hemisphere. As determined using prototype MODIS data, the annual average estimated error of the future Northern Hemisphere snow-cover maps is approximately 8% in the absence of cloud cover, assuming complete snow cover. Preliminary error estimates will be refined after MODIS data have been available for about one year     

A multiple-cascade-classifier system for a robust and partially unsupervised updating of land-cover maps

A system for a regular updating of land-cover maps is proposed that is based on the use of multitemporal remote sensing images. Such a system is able to address the updating problem under the realistic but critical constraint that, for the image to be classified (i.e., the most recent of the considered multitemporal dataset) no ground truth information is available. The system is composed of an ensemble of partially unsupervised classifiers integrated in a multiple-classifier architecture. Each classifier of the ensemble exhibits the following novel characteristics: (1) it is developed in the framework of the cascade-classification approach to exploit the temporal correlation existing between images acquired at different times in the considered area; and (2) it is based on a partially unsupervised methodology capable of accomplishing the classification process under the aforementioned critical constraint. Both a parametric maximum-likelihood (ML) classification approach and a nonparametric radial basis function (RBF) neural-network classification approach are used as basic methods for the development of partially unsupervised cascade classifiers. In addition, in order to generate an effective ensemble of classification algorithms, hybrid ML and RBF neural-network cascade classifiers are defined by exploiting the characteristics of the cascade-classification methodology. The results yielded by the different classifiers are combined by using standard unsupervised combination strategies. This allows the definition of a robust and accurate partially unsupervised classification system capable of analyzing a wide typology of remote sensing data (e.g., images acquired by passive sensors, synthetic aperture radar images, and multisensor and multisource data). Experimental results obtained on a real multitemporal and multisource dataset confirm the effectiveness of the proposed system.     

Employing Code Domain for Contention Resolution in Optical Burst Switched Networks With Detailed Performance Analysis

We propose the implementation of spectral-amplitude-coding optical code division multiple access (SAC-OCDMA) as a contention resolution technique in optical burst switched (OBS) networks. The new system architecture is presented in details where an all-optical methodology for cancelling multiple access interference is proposed. Performance evaluation of the proposed system in both MAC and optical layers is introduced where the overall burst error rate of the system is evaluated in three cases: full, partial, and no code conversion capabilities taking into account the receiver dark current, thermal, and shot noises at the egress nodes. Our results reveal that a considerable improvement in the performance of each core node in the system is achieved by using SAC-OCDMA instead of WDM in the optical layer underneath an OBS based MAC layer. We also conclude that a slight increase in the employed number of code converters enhances the overall system performance noticeably. Finally, optimum values for the number of codes, which lead to minimum overall burst error rate, are reached at different traffic conditions.     

Semi-Supervised Graph-Based Hyperspectral Image Classification

This paper presents a semi-supervised graph-based method for the classification of hyperspectral images. The method is designed to handle the special characteristics of hyperspectral images, namely, high-input dimension of pixels, low number of labeled samples, and spatial variability of the spectral signature. To alleviate these problems, the method incorporates three ingredients, respectively. First, being a kernel-based method, it combats the curse of dimensionality efficiently. Second, following a semi-supervised approach, it exploits the wealth of unlabeled samples in the image, and naturally gives relative importance to the labeled ones through a graph-based methodology. Finally, it incorporates contextual information through a full family of composite kernels. Noting that the graph method relies on inverting a huge kernel matrix formed by both labeled and unlabeled samples, we originally introduce the Nystro umlm method in the formulation to speed up the classification process. The presented semi-supervised-graph-based method is compared to state-of-the-art support vector machines in the classification of hyperspectral data. The proposed method produces better classification maps, which capture the intrinsic structure collectively revealed by labeled and unlabeled points. Good and stable accuracy is produced in ill-posed classification problems (high dimensional spaces and low number of labeled samples). In addition, the introduction of the composite-kernel framework drastically improves results, and the new fast formulation ranks almost linearly in the computational cost, rather than cubic as in the original method, thus allowing the use of this method in remote-sensing applications.     

A Novel Approach to Unsupervised Change Detection Based on a Semisupervised SVM and a Similarity Measure

This paper presents a novel approach to unsupervised change detection in multispectral remote-sensing images. The proposed approach aims at extracting the change information by jointly analyzing the spectral channels of multitemporal images in the original feature space without any training data. This is accomplished by using a selective Bayesian thresholding for deriving a pseudotraining set that is necessary for initializing an adequately defined binary semisupervised support vector machine classifier. Starting from these initial seeds, the performs change detection in the original multitemporal feature space by gradually considering unlabeled patterns in the definition of the decision boundary between changed and unchanged pixels according to a semisupervised learning algorithm. This algorithm models the full complexity of the change-detection problem, which is only partially represented from the seed pixels included in the pseudotraining set. The values of the classifier parameters are then defined according to a novel unsupervised model-selection technique based on a similarity measure between change-detection maps obtained with different settings. Experimental results obtained on different multispectral remote-sensing images confirm the effectiveness of the proposed approach.     

Landsat Large-Area Estimates for Land Cover

A methodology for using ground-gathered and Landsat MSS data to obtain natural resources information over large areas was developed by the USDA, Statistical Reporting Service (SRS) and NASA! NSTL, Earth Resources Laboratory. The SRS's remote-sensing techniques for improving crop area estimates were expanded and modified to obtain land-cover data. These techniques employ statistical relationships ships between field-level ground data and corresponding Landsat pixels to determine classification accuracy and variances for acreage estimates. State-level and land-cover surveys were conducted in Kansas, Missouri, and Arkansas. During the Missouri project, all costs for person-hours, materials, and computer time were tracked for the various analysis steps. Classified Landsat data stored on computer tapes and area estimates with known precision are two products obtained from these surveys.     

Multisource classification of remotely sensed data: fusion ofLandsat TM and SAR images

Proposes a new method for statistical classification of multisource data. The method is suited for land-use classification based on the fusion of remotely sensed images of the same scene captured at different dates from multiple sources. It incorporates a priori information about the likelihood of changes between the acquisition of the different images to be fused. A framework for the fusion of remotely sensed data based on a Bayesian formulation is presented. First, a simple fusion model is given, and then the basic model is extended to take into account the temporal attribute if the different data sources are acquired at different dates. The performance of the model is evaluated by fusing Landsat TM images and ERS-1-SAR images for land-use classification. The fusion model gives significant improvements in the classification error rates compared to the conventional single-source classifiers     

基于光谱与纹理特征的高空间分辨率图像分类算法

针对遥感高分辨率光谱图像的特点,提出了一种将纹理信息与光谱信息相结合的分类算法。对传统的局部二值模式纹理提取方法(LBPV)进行改进,并应用到高分辨率图像的土地覆盖分类中。结果表明,加入LBPV纹理特征的分类算法具有很好的空间连续性以及较高的分类精度。     

基于多分辨率Trace变换的纹理图像分类

针对Trace变换提取的图像特征缺乏对纹理边缘信息描述和计算代价高的问题,利用小波变换对图像轮廓的表征优势,提出了多分辨率Trace变换并应用于纹理图像分类.首先,将小波变换引入到Trace变换中,对纹理图像进行非下采样小波变换,得到不同频率的低频特征子图及高频边缘子图;其次,在各级子图上进行一组泛函的Trace变换,获取纹理图像的融合特征,在获得图像边缘信息的同时避免了Trace变换不同泛函组合计算代价过高的问题;最后,把融合特征送入支持向量机对图像进行分类.实验结果表明,对图像采用多分辨率Trace变换提取的融合特征具有更好的纹理描述能力,相对于传统Trace变换及MCM等对比方法具有更高的鉴别性能,且在时间效率上相对于传统Trace变换有大幅提升.     

A vector quantizer with minimum visible distortion

A method for designing codebooks for vector quantization (VQ) based on minimum error visibility in a reconstructed picture is described. The method uses objective measurements to define visibility for the picture being coded. The proposed VQ is switched type, i.e., the codebook is divided into subcodebooks, each of which is related to a given subrange of error visibility. Codebook optimization is carried out on the basis of a particular definition of visible distortion of the reconstructed image. Subjective judgment of the test results, carried out at 0.5 b/pel bit rate, indicates that the proposed VQ enables low-distortion images to be reconstructed even when subcodebooks with a small number of codewords are used, thus reducing the codebook search time to about 10% of that required by a fixed VQ (both inside and outside the training set)     

一种结合人眼对比度感知特性的彩色图像压缩算法

为了使图像压缩后的效果更加符合人眼感知特性,提出了一种结合人眼对比度敏感视觉特性的图像压缩算法。算法首先结合视觉特性和图像变换域频谱系数特征,提出一种图像的角频率的计算方法,并依据计算的角频率提出一种人眼觉察图像最小误差阈值的计算方法;然后以此阈值作为量化步长,提出一种图像变换域频谱系数的量化方法;最后采用霍夫曼编码算法进行编解码,实现图像的压缩。并对三幅彩色图像进行了仿真实验,结果表明:与JPEG技术相比,三幅彩色图和各分量图的平均压缩比、PSNR和SSIM依次提高了10.4807%、6.9879%和2.6494%。表明提出的结合人眼视觉特性的图像压缩算法是一种较好的、有实用价值的压缩算法。     

改进的FSVM结合语义特征的甲状腺图像分类方法

由于甲状腺发病率高且图像良恶性难以分辨,提出一种改进模糊支持向量机(FSVM)结合语义特征的甲状腺图像分类方法。通过概率潜在语义分析(PLSA)模型对给定的图像训练样本提取语义特征,输入到FSVM中进行分类。其中隶属度是影响FSVM分类精确性的关键,故对其进行改进,在考虑样本点到类中心距离的基础上,对样本点间的紧密度也进行了估计。利用训练生成不同的FSVM测试图像,采用集成方法将分类结果集成,避免了单分类器的分类误差。实验结果表明,该方法可获得较好的分类结果。