Jan Stefanski and Benjamin Mack and Björn Waske, "Optimization of object-based image analysis with Random Forests for land cover mapping", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. in press.

• Abstract
• BibTeX
• DOI

A prerequisite for object-based image analysis is the generation of adequate segments. However, the parameters for the image segmentation algorithms are often manually defined. Therefore, the generation of an ideal segmentation level is usually costly and user-depended. In this paper a strategy for a semi-automatic optimization of object-based classification of multitemporal data is introduced by using Random Forests (RF) and a novel segmentation algorithm. The Superpixel Contour (SPc) algorithm is used to generate a set of different levels of segmentation, using various combinations of parameters in a user-defined range. Finally, the best parameter combination is selected based on the cross-validation-like out-of-bag (OOB) error that is provided by RF. Therefore, the quality of the parameters and the corresponding segmentation level can be assessed in terms of the classification accuracy, without providing additional independent test data. To evaluate the potential of the proposed concept, we focus on land cover classification of two study areas, using multitemporal RapidEye and SPOT 5 images. A classification that is based on eCognition's widely used Multiresolution Segmentation algorithm (MRS) is used for comparison. Experimental results underline that the two segmentation algorithms SPc and MRS perform similar in terms of accuracy and visual interpretation. The proposed strategy that uses the OOB error for the selection of the ideal segmentation level provides similar classification accuracies, when compared to the results achieved by manual-based image segmentation. Overall, the proposed strategy is operational and easy to handle and thus economizes the findings of optimal segmentation parameters for the Superpixel Contour algorithm.

@article{Stefanski2013Optimization,
  author = {Stefanski, Jan and Mack, Benjamin and Waske, Bj\"orn},
  title = {Optimization of object-based image analysis with Random Forests for land cover mapping},
  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year = {in press},
  doi = {10.1109/JSTARS.2013.2253089}
}

Sascha Klemenjak and Björn Waske and Sivia Valero and Jocelyn Chanussot, "Automatic Detection of Rivers in High-Resolution SAR Data", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing., October, 2012. Vol. 5(5), pp. 1364-1372. 2012.

• Abstract
• BibTeX
• DOI

Remote sensing plays a major role in supporting decision-making and surveying compliance of several multilateral environmental treaties. In this paper, we present an approach for supporting monitoring compliance of river networks in context of the European Water Framework Directive. Only a few approaches have been developed for extracting river networks from satellite data and usually they require manual input, which seems not feasible for automatic and operational application. We propose a method for the automatic extraction of river structures in TerraSAR-X data. The method is based on mathematical morphology and supervised image classification, using automatically selected training samples. The method is applied on TerraSAR-X images from two different study sites. In addition, the results are compared to an alternative method, which requires manual user interaction. The detailed accuracy assessment shows that the proposed method achieves accurate results (Kappa $ sim$ 0.7) and performs almost similar in terms of accuracy, when compared to the alternative approach. Moreover, the proposed method can be applied on various datasets (e.g., multitemporal, multisensoral and multipolarized) and does not require any additional user input. Thus, the highly flexible approach is interesting in terms of operational monitoring systems and large scale applications.

@article{Klemenjak2012Automatic,
  author = {Klemenjak, Sascha and Waske, Bj\"orn and Valero, Sivia and Chanussot, Jocelyn},
  title = {Automatic Detection of Rivers in High-Resolution SAR Data},
  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year = {2012},
  volume = {5},
  number = {5},
  pages = {1364--1372},
  doi = {10.1109/JSTARS.2012.2189099}
}

Ribana Roscher and Wolfgang Förstner and Björn Waske, "I2VM: Incremental import vector machines", Image and Vision Computing., May, 2012. Vol. 30(4-5), pp. 263-278. 2012.

• Abstract
• BibTeX
• DOI

We introduce an innovative incremental learner called incremental import vector machines ((IVM)-V-2). The kernel-based discriminative approach is able to deal with complex data distributions. Additionally, the learner is sparse for an efficient training and testing and has a probabilistic output. We particularly investigate the reconstructive component of import vector machines, in order to use it for robust incremental teaming. By performing incremental update steps, we are able to add and remove data samples, as well as update the current set of model parameters for incremental learning. By using various standard benchmarks, we demonstrate how (IVM)-V-2 is competitive or superior to other incremental methods. It is also shown that our approach is capable of managing concept-drifts in the data distributions. (C) 2012 Elsevier B.V. All rights reserved.

@article{Roscher2012I2VM,
  author = {Roscher, Ribana and F\"orstner, Wolfgang and Waske, Bj\"orn},
  title = {I2VM: Incremental import vector machines},
  journal = {Image and Vision Computing},
  year = {2012},
  volume = {30},
  number = {4-5},
  pages = {263--278},
  doi = {10.1016/j.imavis.2012.04.004}
}

Ribana Roscher and Björn Waske and Wolfgang Förstner, "Incremental Import Vector Machines for Classifying Hyperspectral Data", IEEE Transactions on Geoscience and Remote Sensing., September, 2012. Vol. 50(9), pp. 3463-3473. 2012.

• Abstract
• BibTeX
• DOI

In this paper, we propose an incremental learning strategy for import vector machines (IVM), which is a sparse kernel logistic regression approach. We use the procedure for the concept of self-training for sequential classification of hyperspectral data. The strategy comprises the inclusion of new training samples to increase the classification accuracy and the deletion of noninformative samples to be memory and runtime efficient. Moreover, we update the parameters in the incremental IVM model without retraining from scratch. Therefore, the incremental classifier is able to deal with large data sets. The performance of the IVM in comparison to support vector machines (SVM) is evaluated in terms of accuracy, and experiments are conducted to assess the potential of the probabilistic outputs of the IVM. Experimental results demonstrate that the IVM and SVM perform similar in terms of classification accuracy. However, the number of import vectors is significantly lower when compared to the number of support vectors, and thus, the computation time during classification can be decreased. Moreover, the probabilities provided by IVM are more reliable, when compared to the probabilistic information, derived from an SVM's output. In addition, the proposed self-training strategy can increase the classification accuracy. Overall, the IVM and its incremental version is worthwhile for the classification of hyperspectral data.

@article{Roscher2012Incremental,
  author = {Roscher, Ribana and Waske, Bj\"orn and F\"orstner, Wolfgang},
  title = {Incremental Import Vector Machines for Classifying Hyperspectral Data},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2012},
  volume = {50},
  number = {9},
  pages = {3463--3473},
  doi = {10.1109/TGRS.2012.2184292}
}

Björn Waske and Sebastian van der Linden and Carsten Oldenburg and Benjamin Jakimow and Andreas Rabe and Patrick Hostert, "imageRF -- A user-oriented implementation for remote sensing image analysis with Random Forests", Environmental Modelling & Software., July, 2012. Vol. 35, pp. 192-193. 2012.

• Abstract
• BibTeX
• DOI

An IDL implementation for the classification and regression analysis of remote sensing images with Random Forests is introduced. The tool, called imageRF, is platform and license independent and uses generic image file formats. It works well with default parameterization, yet all relevant parameters can be defined in intuitive GUIs. This makes it a user-friendly image processing tool, which is implemented as an add-on in the free EnMAP-Box and may be used in the commercial IDL/ENVI software. (C) 2012 Elsevier Ltd. All rights reserved.

@article{Waske2012imageRF,
  author = {Waske, Bj\"orn and van der Linden, Sebastian and Oldenburg, Carsten and Jakimow, Benjamin and Rabe, Andreas and Hostert, Patrick},
  title = {imageRF -- A user-oriented implementation for remote sensing image analysis with Random Forests},
  journal = {Environmental Modelling \& Software},
  year = {2012},
  volume = {35},
  pages = {192--193},
  doi = {10.1016/j.envsoft.2012.01.014}
}

Thibaut Castaings and Björn Waske and Jon Atli Benediktsson and Jocelyn Chanussot, "On the influence of feature reduction for the classification of hyperspectral images based on the extended morphological profile", International Journal of Remote Sensing. Vol. 31(22), pp. 5975-5991. 2010.

• Abstract
• BibTeX
• DOI

In this study we investigated the classification of hyperspectral data with high spatial resolution. Previously, methods that generate a so-called extended morphological profile (EMP) from the principal components of an image have been proposed to create base images for morphological transformations. However, it can be assumed that the feature reduction (FR) may have a significant effect on the accuracy of the classification of the EMP. We therefore investigated the effect of different FR methods on the generation and classification of the EMP of hyperspectral images from urban areas, using a machine learning-based algorithm for classification. The applied FR methods include: principal component analysis (PCA), nonparametric weighted feature extraction (NWFE), decision boundary feature extraction (DBFE), Gaussian kernel PCA (KPCA) and Bhattacharyya distance feature selection (BDFS). Experiments were run with two classification algorithms: the support vector machine (SVM) and random forest (RF) algorithms. We demonstrate that the commonly used PCA approach seems to be nonoptimal in a large number of cases in terms of classification accuracy, and the other FR methods may be more suitable as preprocessing approaches for the EMP.

@article{Castaings2010influence,
  author = {Castaings, Thibaut and Waske, Bj\"orn and Benediktsson, Jon Atli and Chanussot, Jocelyn},
  title = {On the influence of feature reduction for the classification of hyperspectral images based on the extended morphological profile},
  journal = {International Journal of Remote Sensing},
  year = {2010},
  volume = {31},
  number = {22},
  pages = {5975--5991},
  doi = {10.1080/01431161.2010.512313}
}

Xavier Ceamanos and Björn Waske and Jon Atli Benediktsson and Jocelyn Chanussot and Mathieu Fauvel and Johannes R. Sveinsson, "A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data", International Journal of Image and Data Fusion. Vol. 1(4), pp. 293-307. 2010.

• Abstract
• BibTeX
• DOI

Classification of hyperspectral data using a classifier ensemble that is based on support vector machines (SVMs) are addressed. First, the hyperspectral data set is decomposed into a few data sources according to the similarity of the spectral bands. Then, each source is processed separately by performing classification based on SVM. Finally, all outputs are used as input for final decision fusion performed by an additional SVM classifier. Results of the experiments underline how the proposed SVM fusion ensemble outperforms a standard SVM classifier in terms of overall and class accuracies, the improvement being irrespective of the size of the training sample set. The definition of the data sources resulting from the original data set is also studied.

@article{Ceamanos2010classifier,
  author = {Ceamanos, Xavier and Waske, Bj\"orn and Benediktsson, Jon Atli and Chanussot, Jocelyn and Fauvel, Mathieu and Sveinsson, Johannes R.},
  title = {A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data},
  journal = {International Journal of Image and Data Fusion},
  year = {2010},
  volume = {1},
  number = {4},
  pages = {293--307},
  doi = {10.1080/19479832.2010.485935}
}

Mauro Dalla Mura and Jon Atli Benediktsson and Björn Waske and Lorenzo Bruzzone, "Extended profiles with morphological attribute filters for the analysis of hyperspectral data", International Journal of Remote Sensing. Vol. 31(22), pp. 5975-5991. 2010.

• Abstract
• BibTeX
• DOI

Extended attribute profiles and extended multi-attribute profiles are presented for the analysis of hyperspectral high-resolution images. These extended profiles are based on morphological attribute filters and, through a multi-level analysis, are capable of extracting spatial features that can better model the spatial information, with respect to conventional extended morphological profiles. The features extracted by the proposed extended profiles were considered for a classification task. Two hyperspectral high-resolution datasets acquired for the city of Pavia, Italy, were considered in the analysis. The effectiveness of the introduced operators in modelling the spatial information was proved by the higher classification accuracies obtained with respect to those achieved by a conventional extended morphological profile.

@article{DallaMura2010Extended,
  author = {Dalla Mura, Mauro and Benediktsson, Jon Atli and Waske, Bj\"orn and Bruzzone, Lorenzo},
  title = {Extended profiles with morphological attribute filters for the analysis of hyperspectral data},
  journal = {International Journal of Remote Sensing},
  year = {2010},
  volume = {31},
  number = {22},
  pages = {5975--5991},
  doi = {10.1080/01431161.2010.512425}
}

Mauro Dalla Mura and Jon Atli Benediktsson and Björn Waske and Lorenzo Bruzzone, "Morphological Attribute Profiles for the Analysis of Very High Resolution Images", IEEE Transactions on Geoscience and Remote Sensing., October, 2010. Vol. 48(10), pp. 3747-3762. 2010.

• Abstract
• BibTeX
• DOI

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.

@article{DallaMura2010Morphological,
  author = {Dalla Mura, Mauro and Benediktsson, Jon Atli and Waske, Bj\"orn and Bruzzone, Lorenzo},
  title = {Morphological Attribute Profiles for the Analysis of Very High Resolution Images},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2010},
  volume = {48},
  number = {10},
  pages = {3747--3762},
  doi = {10.1109/TGRS.2010.2048116}
}

Sivia Valero and Jocelyn Chanussot and Jon Atli Benediktsson and Huges Talbot and Björn Waske, "Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images", Pattern Recognition Letters., July, 2010. Vol. 31(10), pp. 1120-1127. 2010.

• Abstract
• BibTeX
• DOI

Very high spatial resolution (VHR) images allow to feature man-made structures such as roads and thus enable their accurate analysis. Geometrical characteristics can be extracted using mathematical morphology. However, the prior choice of a reference shape (structuring element) introduces a shape-bias. This paper presents a new method for extracting roads in Very High Resolution remotely sensed images based on advanced directional morphological operators. The proposed approach introduces the use of Path Openings and Path Closings in order to extract structural pixel information. These morphological operators remain flexible enough to fit rectilinear and slightly curved structures since they do not depend on the choice of a structural element shape. As a consequence, they outperform standard approaches using rotating rectangular structuring elements. The method consists in building a granulometry chain using Path Openings and Path Closing to construct Morphological Profiles. For each pixel, the Morphological Profile constitutes the feature vector on which our road extraction is based. (C) 2009 Published by Elsevier B.V.

@article{Valero2010Advanced,
  author = {Valero, Sivia and Chanussot, Jocelyn and Benediktsson, Jon Atli and Talbot, Huges and Waske, Bj\"orn},
  title = {Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images},
  journal = {Pattern Recognition Letters},
  year = {2010},
  volume = {31},
  number = {10},
  pages = {1120--1127},
  doi = {10.1016/j.patrec.2009.12.018}
}

Björn Waske and Sebastian van der Linden and Jon Atli Benediktsson and Andreas Rabe and Patrick Hostert, "Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data", IEEE Transactions on Geoscience and Remote Sensing., July, 2010. Vol. 48(7), pp. 2880-2889. 2010.

• Abstract
• BibTeX
• DOI

The accuracy of supervised land cover classifications depends on factors such as the chosen classification algorithm, adequate training data, the input data characteristics, and the selection of features. Hyperspectral imaging provides more detailed spectral and spatial information on the land cover than other remote sensing resources. Over the past ten years, traditional and formerly widely accepted statistical classification methods have been superseded by more recent machine learning algorithms, e.g., support vector machines (SVMs), or by multiple classifier systems (MCS). This can be explained by limitations of statistical approaches with regard to high-dimensional data, multimodal classes, and often limited availability of training data. In the presented study, MCSs based on SVM and random feature selection (RFS) are applied to explore the potential of a synergetic use of the two concepts. We investigated how the number of selected features and the size of the MCS influence classification accuracy using two hyperspectral data sets, from different environmental settings. In addition, experiments were conducted with a varying number of training samples. Accuracies are compared with regular SVM and random forests. Experimental results clearly demonstrate that the generation of an SVM-based classifier system with RFS significantly improves overall classification accuracy as well as producer's and user's accuracies. In addition, the ensemble strategy results in smoother, i.e., more realistic, classification maps than those from stand-alone SVM. Findings from the experiments were successfully transferred onto an additional hyperspectral data set.

@article{Waske2010Sensitivity,
  author = {Waske, Bj\"orn and van der Linden, Sebastian and Benediktsson, Jon Atli and Rabe, Andreas and Hostert, Patrick},
  title = {Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2010},
  volume = {48},
  number = {7},
  pages = {2880--2889},
  doi = {10.1109/TGRS.2010.2041784}
}

Thomas Udelhoven and Sebastian van der Linden and Björn Waske and Marion Stellmes and Lucien Hoffmann, "Hypertemporal Classification of Large Areas Using Decision Fusion", IEEE Geoscience and Remote Sensing Letters., July, 2009. Vol. 6(3), pp. 592-596. 2009.

• Abstract
• BibTeX
• DOI

A novel multiannual land-cover-classification scheme for classifying hypertemporal image data is suggested, which is based on a supervised decision fusion (DF) approach. This DF approach comprises two steps: First, separate support vector machines (SVMs) are trained for normalized difference vegetation index (NDVI) time-series and mean annual temperature values of three consecutive years. In the second step, the information of the preliminary continuous SVM outputs, which represent posterior probabilities of the class assignments, is fused using a second-level SVM classifier. We tested the approach using the 10-day maximum-value NDVI composites from the "Mediterranean Extended Daily one-km Advanced Very High Resolution Radiometer Data Set" (MEDOKADS). The approach increases the classification accuracy and robustness compared with another DF method (simple majority voting) and with a single SVM expert that is trained for the same multiannual periods. The results clearly demonstrate that DF is a reliable technique for large-area mapping using hypertemporal data sets.

@article{Udelhoven2009Hypertemporal,
  author = {Udelhoven, Thomas and van der Linden, Sebastian and Waske, Bj\"orn and Stellmes, Marion and Hoffmann, Lucien},
  title = {Hypertemporal Classification of Large Areas Using Decision Fusion},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2009},
  volume = {6},
  number = {3},
  pages = {592--596},
  doi = {10.1109/LGRS.2009.2021960}
}

Björn Waske and Matthias Braun, "Classifier ensembles for land cover mapping using multitemporal SAR imagery", ISPRS Journal of Photogrammetry and Remote Sensing., September, 2009. Vol. 64(5), pp. 450-457. 2009.

• Abstract
• BibTeX
• DOI

SAR data are almost independent from weather conditions, and thus are well suited for mapping of seasonally changing variables such as land cover. In regard to recent and upcoming missions, multitemporal and multi-frequency approaches become even more attractive. In the present study, classifier ensembles (i.e., boosted decision tree and random forests) are applied to multi-temporal C-band SAR data, from different study sites and years. A detailed accuracy assessment shows that classifier ensembles, in particularly random forests, outperform standard approaches like a single decision tree and a conventional maximum likelihood classifier by more than 10% independently from the site and year. They reach up to almost 84% of overall accuracy in rural areas with large plots. Visual interpretation confirms the statistical accuracy assessment and reveals that also typical random noise is considerably reduced. In addition the results demonstrate that random forests are less sensitive to the number of training samples and perform well even with only a small number. Random forests are computationally highly efficient and are hence considered very well suited for land cover classifications of future multifrequency and multitemporal stacks of SAR imagery. (C) 2009 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.

@article{Waske2009Classifier,
  author = {Waske, Bj\"orn and Braun, Matthias},
  title = {Classifier ensembles for land cover mapping using multitemporal SAR imagery},
  journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
  year = {2009},
  volume = {64},
  number = {5},
  pages = {450--457},
  doi = {10.1016/j.isprsjprs.2009.01.003}
}

Björn Waske and Jon Atli Benediktsson and Kolbeinn Arnason and Johannes R. Sveinsson, "Mapping of hyperspectral AVIRIS data using machine-learning algorithms", Canadian Journal of Remote Sensing. Vol. 35, pp. 106-116. 2009.

• Abstract
• BibTeX
• DOI

Hyperspectral imaging provides detailed spectral and spatial information from the land cover that enables a precise differentiation between various surface materials. on the other hand, the performance of traditional and widely used statistical classification methods is often limited in this context, and thus alternative methods are required. In the study presented here, the performance of two machine-learning techniques, namely support vector machines (SVMs) and random forests (RFs), is investigated and the classification results are compared with those from well-known methods (i.e., maximum likelihood classifier and spectral angle mapper). The classifiers are applied to an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) dataset that was acquired near the Hekla volcano in Iceland. The results clearly show the advantages of the two proposed classifier algorithms in terms of accuracy. They significantly outperform the other methods and achieve overall accuracies of approximately 90%. Although SVM and RF show some diversity in the classification results, the global performance of the two classifiers is very similar. Thus, both methods can be considered attractive for the classification of hyperspectral data.

@article{Waske2009Mapping,
  author = {Waske, Bj\"orn and Benediktsson, Jon Atli and Arnason, Kolbeinn and Sveinsson, Johannes R.},
  title = {Mapping of hyperspectral AVIRIS data using machine-learning algorithms},
  journal = {Canadian Journal of Remote Sensing},
  year = {2009},
  volume = {35},
  pages = {106--116},
  doi = {10.5589/m09-018}
}

Björn Waske and Sebastian van der Linden, "Classifying multilevel imagery from SAR and optical sensors by decision fusion", IEEE Transactions on Geoscience and Remote Sensing., May, 2008. Vol. 46(5), pp. 1457-1466. 2008.

• Abstract
• BibTeX
• DOI

A strategy for the joint classification of multiple segmentation levels from multisensor imagery is introduced by using synthetic aperture radar and optical data. At first, the two data sets are separately segmented, creating independent aggregation levels at different scales. Each individual level from the two sensors is then preclassified by a support vector machine (SVM). The original outputs of each SVM, i.e., images showing the distances of the pixels to the hyperplane fitted by the SVM, are used in a decision fusion to determine the final classes. The fusion strategy is based on the application of an additional classifier, which is applied on the preclassification results. Both a second SVM and random forests (RF) were tested for the decision fusion. The results are compared with SVM and RF applied to the full data set without preclassification. Both the integration of multilevel information and the use of multisensor imagery increase the overall accuracy. It is shown that the classification of multilevel-multisource data sets with SVM and RF is feasible and does not require a definition of ideal aggregation levels. The proposed decision fusion approach that applies RF to the preclassification outperforms all other approaches.

@article{Waske2008Classifying,
  author = {Waske, Bj\"orn and van der Linden, Sebastian},
  title = {Classifying multilevel imagery from SAR and optical sensors by decision fusion},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2008},
  volume = {46},
  number = {5},
  pages = {1457--1466},
  doi = {10.1109/TGRS.2008.916089}
}

Sebastian van der Linden and Andreas Janz and Björn Waske and Michael Eiden and Patrick Hostert, "Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines", Journal of Applied Remote Sensing. Vol. 1, pp. 013543. 2007.

• Abstract
• BibTeX
• DOI

Classifying remotely sensed images from urban environments is challenging. Urban land cover classes are spectrally heterogeneous and materials from different classes have similar spectral properties. Image segmentation has become a common preprocessing step that helped to overcome such problems. However, little attention has been paid to impacts of segmentation on the data's spectral information content. Here, urban hyperspectral data is spectrally classified using support vector machines (SVM). By training a SVM on pixel information and applying it to the image before segmentation and after segmentation at different levels, the classification framework is maintained and the influence of the spectral generalization during image segmentation hence directly investigated. In addition, a straightforward multi-level approach was performed, which combines information from different levels into one final map. A stratified accuracy assessment by urban structure types is applied. The classification of the unsegmented data achieves an overall accuracy of 88.7%. Accuracy of the segment-based classification is lower and decreases with increasing segment size. Highest accuracies for the different urban structure types are achieved at varying segmentation levels. The accuracy of the multi-level approach is similar to that of unsegmented data but comprises the positive effects of more homogeneous segment-based classifications at different levels in one map.

@article{Linden2007Classifying,
  author = {van der Linden, Sebastian and Janz, Andreas and Waske, Bj\"orn and Eiden, Michael and Hostert, Patrick},
  title = {Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines},
  journal = {Journal of Applied Remote Sensing},
  year = {2007},
  volume = {1},
  pages = {013543},
  doi = {10.1117/1.2813466}
}

Björn Waske and Jon Atli Benediktsson, "Fusion of support vector machines for classification of multisensor data", IEEE Transactions on Geoscience and Remote Sensing., December, 2007. Vol. 45(12), pp. 3858-3866. 2007.

• Abstract
• BibTeX
• DOI

The classification of multisensor data sets, consisting of multitemporal synthetic aperture radar data and optical imagery, is addressed. The concept is based on the decision fusion of different outputs. Each data source is treated separately and classified by a support vector machine (SVM). Instead of fusing the final classification outputs (i.e., land cover classes), the original outputs of each SVM discriminant function are used in the subsequent fusion process. This fusion is performed by another SVM, which is trained on the a priori outputs. In addition, two voting schemes are applied to create the final classification results. The results are compared with well-known parametric and nonparametric classifier methods, i.e., decision trees, the maximum-likelihood classifier, and classifier ensembles. The proposed SVM-based fusion approach outperforms all other approaches and significantly improves the results of a single SVM, which is trained on the whole multisensor data set.

@article{Waske2007Fusion,
  author = {Waske, Bj\"orn and Benediktsson, Jon Atli},
  title = {Fusion of support vector machines for classification of multisensor data},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2007},
  volume = {45},
  number = {12},
  pages = {3858--3866},
  doi = {10.1109/TGRS.2007.898446}
}

Björn Waske and Matthias Braun and Gunter Menz, "A segment-based speckle filter using multisensoral remote sensing imagery", IEEE Geoscience and Remote Sensing Letters., April, 2007. Vol. 4(2), pp. 231-235. 2007.

• Abstract
• BibTeX
• DOI

In the proposed approach, the well-known enhanced Lee filter is modified to allow the integration of feature outlines-previously extracted from segmented optical images. The filter is applied to several ENVISAT ASAR images that cover urban, agricultural, and forest areas during different plant phenological stages. The performance of this segment-based speckle filter is compared to those of other filters using ratio images, visual interpretation, and statistical indexes. The approach reduces the loss of radiometry and spatial information. It performs comparable to more complex methods and outperforms common techniques.

@article{Waske2007segment,
  author = {Waske, Bj\"orn and Braun, Matthias and Menz, Gunter},
  title = {A segment-based speckle filter using multisensoral remote sensing imagery},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2007},
  volume = {4},
  number = {2},
  pages = {231--235},
  doi = {10.1109/LGRS.2006.888849}
}