University of Iceland
Electrical and Computer Engineering
This paper addresses the use of HySenS airborne hyperspectral data for environmental urban monitoring. It is known that hyperspectral data can help to characterize some of the relations between soil composition, vegetation... more
This paper addresses the use of HySenS airborne hyperspectral data for environmental urban monitoring. It is known that hyperspectral data can help to characterize some of the relations between soil composition, vegetation characteristics, and natural/artificial materials in urbanized areas. During the project we collected DAIS and ROSIS data over the urban test area of Pavia, Northern Italy, though due to a late delivery of ROSIS data only DAIS data was used in this work. Here we show results referring to an accurate characterization and classification of land cover/use, using different supervised approaches, exploiting spectral as well as spatial information. We demonstrate the possibility to extract from the hyperspectral data information which is very useful for environmental characterization of urban areas.
- by Fabio Dell'Acqua and +2
- •
- Hyperspectral Data
Artajiicial neural networks (ANNs) are discussed in terms of classification of brain auditcny euent-related potentiaa0 (ERPs) . A new ANN architecture fw the classzjication of ERF's is proposed. The new architecture is called the parallel... more
Artajiicial neural networks (ANNs) are discussed in terms of classification of brain auditcny euent-related potentiaa0 (ERPs) . A new ANN architecture fw the classzjication of ERF's is proposed. The new architecture is called the parallel frincipal component neural network (PPCNN) . The use of the PPCNN for classzjication of ERP data obtained ,fiom both normal control subjects and chronic schizophrenic patients is discussed. Lxpm'mental results are given. 0 1997 ESeuiff Scienre Ltd for IPEMB. All tights reserved.
The classification of very high-resolution remote sensing images from urban areas is addressed by considering the fusion of multiple classifiers which provide redundant or complementary results. The proposed fusion approach is in two... more
The classification of very high-resolution remote sensing images from urban areas is addressed by considering the fusion of multiple classifiers which provide redundant or complementary results. The proposed fusion approach is in two steps. In a first step, data are processed by each classifier separately and the algorithms provide for each pixel membership degrees for the considered classes. Then, in a second step, a fuzzy decision rule is used to aggregate the results provided by the algorithms according to the classifiers' capabilities. In this paper, a general framework for combining information from several individual classifiers in multiclass classification is proposed. It is based on the definition of two measures of accuracy. The first one is a point-wise measure which estimates for each pixel the reliability of the information provided by each classifier. By modeling the output of a classifier as a fuzzy set, this point-wise reliability is defined as the degree of uncertainty of the fuzzy set. The second measure estimates the global accuracy of each classifier. It is defined a priori by the user. Finally, the results are aggregated with an adaptive fuzzy operator ruled by these two accuracy measures. The method is tested and validated with two classifiers on IKONOS images from urban areas. The proposed method improves the classification results when compared with the separate use of the different classifiers. The approach is also compared to several other fuzzy fusion schemes.
Morphological attribute profiles (APs) are defined as a generalization of the recently proposed morphological profiles (MPs). APs provide a multilevel characterization of an image created by the sequential application of morphological... more
Morphological attribute profiles (APs) are defined as a generalization of the recently proposed morphological profiles (MPs). APs provide a multilevel characterization of an image created by the sequential application of morphological attribute filters that can be used to model different kinds of the structural information. According to the type of the attributes considered in the morphological attribute transformation, different parametric features can be modeled. The generation of APs, thanks to an efficient implementation, strongly reduces the computational load required for the computation of conventional MPs. Moreover, the characterization of the image with different attributes leads to a more complete description of the scene and to a more accurate modeling of the spatial information than with the use of conventional morphological filters based on a predefined structuring element. Here, the features extracted by the proposed operators were used for the classification of two very high resolution panchromatic images acquired by Quickbird on the city of Trento, Italy. The experimental analysis proved the usefulness of APs in modeling the spatial information present in the images. The classification maps obtained by considering different APs result in a better description of the scene (both in terms of thematic and geometric accuracy) than those obtained with an MP.
Classification of hyperspectral data with high spatial resolution from urban areas is investigated. A method based on mathematical morphology for preprocessing of the hyperspectral data is proposed. In this approach, opening and closing... more
Classification of hyperspectral data with high spatial resolution from urban areas is investigated. A method based on mathematical morphology for preprocessing of the hyperspectral data is proposed. In this approach, opening and closing morphological transforms are used in order to isolate bright (opening) and dark (closing) structures in images, where bright/dark means brighter/darker than the surrounding features in the images. A morphological profile is constructed based on the repeated use of openings and closings with a structuring element of increasing size, starting with one original image. In order to apply the morphological approach to hyperspectral data, principal components of the hyperspectral imagery are computed. The most significant principal components are used as base images for an extended morphological profile, i.e., a profile based on more than one original image. In experiments, two hyperspectral urban datasets are classified. The proposed method is used as a preprocessing method for a neural network classifier and compared to more conventional classification methods with different types of statistical computations and feature extraction.
A method is proposed for the classification of urban hyperspectral data with high spatial resolution. The approach is an extension of previous approaches and uses both the spatial and spectral information for classification. One previous... more
A method is proposed for the classification of urban hyperspectral data with high spatial resolution. The approach is an extension of previous approaches and uses both the spatial and spectral information for classification. One previous approach is based on using several principal components (PCs) from the hyperspectral data and building several morphological profiles (MPs). These profiles can be used all together in one extended MP. A shortcoming of that approach is that it was primarily designed for classification of urban structures and it does not fully utilize the spectral information in the data. Similarly, the commonly used pixelwise classification of hyperspectral data is solely based on the spectral content and lacks information on the structure of the features in the image. The proposed method overcomes these problems and is based on the fusion of the morphological information and the original hyperspectral data, i.e., the two vectors of attributes are concatenated into one feature vector. After a reduction of the dimensionality, the final classification is achieved by using a support vector machine classifier. The proposed approach is tested in experiments on ROSIS data from urban areas. Significant improvements are achieved in terms of accuracies when compared to results obtained for approaches based on the use of MPs based on PCs only and conventional spectral classification. For instance, with one data set, the overall accuracy is increased from 79% to 83% without any feature reduction and to 87% with feature reduction. The proposed approach also shows excellent results with a limited training set.
Random Forests are considered for classification of multisource remote sensing and geographic data. Various ensemble classification methods have been proposed in recent years. These methods have been proven to improve classification... more
Random Forests are considered for classification of multisource remote sensing and geographic data. Various ensemble classification methods have been proposed in recent years. These methods have been proven to improve classification accuracy considerably. The most widely used ensemble methods are boosting and bagging. Boosting is based on sample re-weighting but bagging uses bootstrapping. The Random Forest classifier uses bagging, or bootstrap aggregating, to form an ensemble of classification and regression tree (CART)-like classifiers. In addition, it searches only a random subset of the variables for a split at each CART node, in order to minimize the correlation between the classifiers in the ensemble. This method is not sensitive to noise or overtraining, as the resampling is not based on weighting. Furthermore, it is computationally much lighter than methods based on boosting and somewhat lighter than simple bagging. In the paper, the use of the Random Forest classifier for land cover classification is explored. We compare the accuracy of the Random Forest classifier to other better-known ensemble methods on multisource remote sensing and geographic data.
Kernel principal component analysis (KPCA) is investigated for feature extraction from hyperspectral remote sensing data. Features extracted using KPCA are classified using linear support vector machines. In one experiment, it is shown... more
Kernel principal component analysis (KPCA) is investigated for feature extraction from hyperspectral remote sensing data. Features extracted using KPCA are classified using linear support vector machines. In one experiment, it is shown that kernel principal component features are more linearly separable than features extracted with conventional principal component analysis. In a second experiment, kernel principal components are used to construct the extended morphological profile (EMP). Classification results, in terms of accuracy, are improved in comparison to original approach which used conventional principal component analysis for constructing the EMP. Experimental results presented in this paper confirm the usefulness of the KPCA for the analysis of hyperspectral data. For the one data set, the overall classification accuracy increases from 79% to 96% with the proposed approach.
Classification of hyperspectral data with high spatial resolution from urban areas is discussed. A previously proposed approach is based on using several principal components from the hyperspectral data to build morphological profiles.... more
Classification of hyperspectral data with high spatial resolution from urban areas is discussed. A previously proposed approach is based on using several principal components from the hyperspectral data to build morphological profiles. These profiles are used all together in one extended morphological profile, which is then classified by a neural network. A shortcoming of the approach is that it is primarily designed for classification of structures and it does not fully utilize the spectral information in the data. An extension is proposed in this paper in order to overcome the problems with the extended morphological profile approach. The proposed method is based on applying data fusion on the original data and the morphological information, after feature extraction. The proposed approach is tested in experiments on two different high resolution remote sensing data sets from urban areas.
The combination of multisource remote sensing and geographic data is believed to offer improved accuracies in land cover classification. For such classification, the conventional parametric statistical classifiers, which have been applied... more
The combination of multisource remote sensing and geographic data is believed to offer improved accuracies in land cover classification. For such classification, the conventional parametric statistical classifiers, which have been applied successfully in remote sensing for the last two decades, are not appropriate, since a convenient multivariate statistical model does not exist for the data. In this paper, several single and multiple classifiers, that are appropriate for the classification of multisource remote sensing and geographic data are considered. The focus is on multiple classifiers: bagging algorithms, boosting algorithms, and consensus-theoretic classifiers. These multiple classifiers have different characteristics. The performance of the algorithms in terms of accuracies is compared for two multisource remote sensing and geographic datasets. In the experiments, the multiple classifiers outperform the single classifiers in terms of overall accuracies.
Recently, decision level fusion has shown great potential to increase classification accuracy beyond the level reached by individual classifiers. A considerable body of literature exists on identifying optimal ways to combine classifiers.... more
Recently, decision level fusion has shown great potential to increase classification accuracy beyond the level reached by individual classifiers. A considerable body of literature exists on identifying optimal ways to combine classifiers. However, the selection of the classifiers to be combined is equally, if not more, crucial if an improvement is to be made for certain classifier combination schemes. Agreement among classifiers can inhibit the gains obtained regardless of the method used to combine them. In this work, the level of agreement between different classifiers used in remote sensing is assessed based on statistical measures. A study is performed in which an image is classified by several methods with different degrees of agreement between them. The results are then combined using decision fusion schemes and the increase of accuracy is observed for each combination of the individual classifications.
The surface of Mars is currently being imaged with an unprecedented combination of spectral and spatial resolution. This high resolution, and its spectral range, give the ability to pinpoint chemical species on the surface and the... more
The surface of Mars is currently being imaged with an unprecedented combination of spectral and spatial resolution. This high resolution, and its spectral range, give the ability to pinpoint chemical species on the surface and the atmosphere of Mars moreaccurately than before. The subject of this paper is to present a method to extract informations on these chemicals from hyperspectral images. A first approach, based on Independent Component Analysis (ICA) [1], is able to extract artifacts and locations of CO2 and H2O ices. However, the main independence assumption and some basic properties (like the positivity of images and spectra) being unverified, the reliability of all the independent components (ICs) is weak. For improving the component extraction and consequently the endmember classification, a combination of spatial ICA with spectral Bayesian Positive Source Separation (BPSS) [2] is proposed. To reduce the computational burden, the basic idea is to use spatial ICA yielding a rough classification of pixels, which allows selection of small, but relevant, number of pixels and then BPSS is applied for the estimation of the source spectra using the spectral mixtures provided by this reduced set of pixels. Finally, the abundances of the components is assessed on the whole pixels of the images. Results of this approach are shown and evaluated by comparison with available reference spectra.
Hybrid classification methods based on consensus from several data sources are considered. Each data source is at first treated separately and modeled using statistical methods. Then weighting mechanisms are used to control the influence... more
Hybrid classification methods based on consensus from several data sources are considered. Each data source is at first treated separately and modeled using statistical methods. Then weighting mechanisms are used to control the influence of each data source in the combined classification. The weights are optimized in order to improve the combined classification accuracies. Both linear and nonlinear optimization methods are considered and used in classification of two multisource remote sensing and geographic data sets. A nonlinear method which utilizes a neural network gives excellent experimental results. The hybrid statistical/neural method outperforms all other methods in terms of test accuracies in the experiments.
Multisource classification methods based on neural networks and statistical modeling are considered. For these methods, the individual data sources are at first treated separately and modeled by statistical methods. Then several decision... more
Multisource classification methods based on neural networks and statistical modeling are considered. For these methods, the individual data sources are at first treated separately and modeled by statistical methods. Then several decision fusion schemes are applied to combine the information from the individual data sources. These schemes include weighted consensus theory where the weights of the individual data sources reflect the reliability of the sources. The weights are optimized in order to improve the combined classification accuracies. Other considered decision fusion schemes are based on two-stage approaches which use voting in the first stage and reject samples if either the majority or all of the classifiers for the data sources do not agree on a classification of a sample. For the second stage, a neural network is used to classify the rejected samples. The proposed methods are applied in the classification of multisource and hyperdimensional data sets, and the results compared to accuracies obtained with conventional classification schemes.
A new spectral-spatial classification scheme for hyperspectral images is proposed. The method combines the results of a pixel wise support vector machine classification and the segmentation map obtained by partitional clustering using... more
A new spectral-spatial classification scheme for hyperspectral images is proposed. The method combines the results of a pixel wise support vector machine classification and the segmentation map obtained by partitional clustering using majority voting. The ISODATA algorithm and Gaussian mixture resolving techniques are used for image clustering. Experimental results are presented for two hyperspectral airborne images. The developed classification scheme improves the classification accuracies and provides classification maps with more homogeneous regions, when compared to pixel wise classification. The proposed method performs particularly well for classification of images with large spatial structures and when different classes have dissimilar spectral responses and a comparable number of pixels.
Classification of panchromatic high-resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is based on three steps. First, the composition of geodesic opening and closing... more
Classification of panchromatic high-resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is based on three steps. First, the composition of geodesic opening and closing operations of different sizes is used in order to build a differential morphological profile that records image structural information. Although, the original panchromatic image only has one data channel, the use of the composition operations will give many additional channels, which may contain redundancies. Therefore, feature extraction or feature selection is applied in the second step. Both discriminant analysis feature extraction and decision boundary feature extraction are investigated in the second step along with a simple feature selection based on picking the largest indexes of the differential morphological profiles. Third, a neural network is used to classify the features from the second step. The proposed approach is applied in experiments on high-resolution Indian Remote Sensing 1C (IRS-1C) and IKONOS remote sensing data from urban areas. In experiments, the proposed method performs well in terms of classification accuracies. It is seen that relatively few features are needed to achieve the same classification accuracies as in the original feature space.
Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in less than 30 years from being a sparse research tool into a commodity product available to a broad user community. Currently, there is a need for... more
Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in less than 30 years from being a sparse research tool into a commodity product available to a broad user community. Currently, there is a need for standardized data processing techniques able to take into account the special properties of hyperspectral data. In this paper, we provide a seminal view on recent advances in techniques for hyperspectral image processing. Our main focus is on the design of techniques able to deal with the highdimensional nature of the data, and to integrate the spatial and spectral information. Performance of the discussed techniques is evaluated in different analysis scenarios. To satisfy time-critical constraints in specific applications, we also develop efficient parallel implementations of some of the discussed algorithms. Combined, these parts provide an excellent snapshot of the state-of-the-art in those areas, and offer a thoughtful perspective on future potentials and emerging challenges in the design of robust hyperspectral imaging algorithms.
Classification of hyperspectral remote sensing data with support vector machines (SVMs) is investigated. SVMs have been introduced recently in the field of remote sensing image processing. Using the kernel method, SVMs map the data into... more
Classification of hyperspectral remote sensing data with support vector machines (SVMs) is investigated. SVMs have been introduced recently in the field of remote sensing image processing. Using the kernel method, SVMs map the data into higher dimensional space to increase the separability and then fit an optimal hyperplane to separate the data. In this paper, two kernels have been considered. The generalization capability of SVMs as well as the ability of SVMs to deal with high dimensional feature spaces have been tested in the situation of very limited training set. SVMs have been tested on real hyperspectral data. The experimental results show that SVMs used with the two kernels are appropriate for remote sensing classification problems.
A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on... more
A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.