Centre de documentation
scientifique

Multistrategy ensemble regression for mapping of built-up density and height with Sentinel-2 data / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 170 (December 2020) . - pp 57-71 Titre : Multistrategy ensemble regression for mapping of built-up density and height with Sentinel-2 data Type de document : Article/Communication Auteurs : Christian Geiss, Auteur ; Henrik Schrade, Auteur ; Patrick Aravena Pelizari, Auteur ; Hannes Taubenböck, Auteur Année de publication : 2020 Article en page(s) : pp 57-71 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Allemagne [Termes IGN] apprentissage automatique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] hauteur du bâti [Termes IGN] image multibande [Termes IGN] image Sentinel-MSI [Termes IGN] image TanDEM-X [Termes IGN] modèle de régression [Termes IGN] morphologie urbaine [Termes IGN] pondération [Termes IGN] processus gaussien [Termes IGN] zone urbaine dense Résumé : (Auteur) In this paper, we establish a workflow for estimation of built-up density and height based on multispectral Sentinel-2 data. To do so, we render the estimation of built-up density and height as a supervised learning problem. Given the rational level of measurement of those two target variables, the regression estimation problem is regarded as finding the mapping between an incoming vector, i.e., ubiquitously available features computed from Sentinel-2 data, and an observable output (i.e., training set), which is derived over spatially limited areas in an automated manner. As such, training sets are automatically generated from a joint exploitation of TanDEM-X mission elevation data and Sentinel-2 imagery, and, as an alternative, from cadastral sources. The training sets are used to regress the target variables for spatial processing units which correspond to urban neighborhood scales. From a methodological point of view, we introduce a novel ensemble regression approach, i.e., multistrategy ensemble regression (MSER), based on advanced machine learning-based regression algorithms including Random Forest Regression, Support Vector Regression, Gaussian Process Regression, and Neural Network Regression. To establish a robust ensemble, those algorithms are learned with a modified version of the AdaBoost.RT algorithm. However, to reliably ensure diversity between single boosted regressors, we include a random feature subspace method in the procedure. In contrast to existing approaches, we selectively prune non-favorable regressors trained during the boosting procedure and calculate the final prediction by a weighted mean function on the residual models to ensure enhanced accuracy properties of predictions. Finally, outputs are concatenated into a single prediction with a decision fusion strategy. Experimental results are obtained from four test areas which cover the settlement areas of the four largest German cites, i.e., Berlin, Hamburg, Munich, and Cologne. The results unambiguously underline the beneficial properties of the MSER approach, since all best predictions were obtained with a boosted regressor in conjunction with a decision fusion strategy in a comparative setup. The mean absolute errors of corresponding models vary between 3 and 16% and 1–5.4 m with respect to built-up density and height, respectively, depending on the validation strategy, size of the spatial processing units, and test area. Also in a domain adaptation setup (i.e., when learning a model over a source domain and applying it over a geographically different target domain) numerous predictions show comparable accuracy levels as predictions obtained within a source domain. This further underlines the viability to transfer a model and, thus, enable a substitution of the training data in the target domains. Numéro de notice : A2020-704 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.10.004 Date de publication en ligne : 22/10/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.10.004 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96231 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020121	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 151 (May 2019) . - pp 42 - 58 Titre : Virtual Support Vector Machines with self-learning strategy for classification of multispectral remote sensing imagery Type de document : Article/Communication Auteurs : Christian Geiss, Auteur ; Patrick Aravena Pelizari, Auteur ; Lukas Blickensdörfer, Auteur ; Hannes Taubenböck, Auteur Année de publication : 2019 Article en page(s) : pp 42 - 58 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage automatique [Termes IGN] classification [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] Cologne [Termes IGN] échantillon [Termes IGN] échantillonnage [Termes IGN] image à très haute résolution [Termes IGN] image multibande [Termes IGN] invariant [Termes IGN] Kenya [Termes IGN] séparateur à vaste marge Résumé : (Auteur) We follow the idea of learning invariant decision functions for remote sensing image classification with Support Vector Machines (SVM). To do so, we generate artificially transformed samples (i.e., virtual samples) from available prior knowledge. Labeled samples closest to the separating hyperplane with maximum margin (i.e., the Support Vectors) are identified by learning an initial SVM model. The Support Vectors are used for generating virtual samples by perturbing the features to which the model should be invariant. Subsequently, the model is relearned using the Support Vectors and the virtual samples to eventually alter the hyperplane with maximum margin and enhance generalization capabilities of decision functions. In contrast to existing approaches, we establish a self-learning procedure to ultimately prune non-informative virtual samples from a possibly arbitrary invariance generation process to allow for robust and sparse model solutions. The self-learning strategy jointly considers a similarity and margin sampling constraint. In addition, we innovatively explore the invariance generation process in the context of an object-based image analysis framework. Image elements (i.e., pixels) are aggregated to image objects (as represented by segments/superpixels) with a segmentation algorithm. From an initial singular segmentation level, invariances are encoded by varying hyperparameters of the segmentation algorithm in terms of scale and shape. Experimental results are obtained from two very high spatial resolution multispectral data sets acquired over the city of Cologne, Germany, and the Hagadera Refugee Camp, Kenya. Comparative model accuracy evaluations underline the favorable performance properties of the proposed methods especially in settings with very few labeled samples. Numéro de notice : A2019-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.03.001 Date de publication en ligne : 12/03/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.03.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92666 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019051	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2019053	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2019052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt