Centre de documentation
scientifique

Learning from the past: crowd-driven active transfer learning for semantic segmentation of multi-temporal 3D point clouds / Michael Kölle in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 259 - 266 Titre : Learning from the past: crowd-driven active transfer learning for semantic segmentation of multi-temporal 3D point clouds Type de document : Article/Communication Auteurs : Michael Kölle, Auteur ; Volker Walter, Auteur ; Uwe Soergel, Auteur Année de publication : 2022 Article en page(s) : pp 259 - 266 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] apprentissage automatique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données étiquetées d'entrainement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] données multitemporelles [Termes IGN] orthoimage couleur [Termes IGN] production participative [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] traitement de données localisées Résumé : (auteur) The main bottleneck of machine learning systems, such as convolutional neural networks, is the availability of labeled training data. Hence, much effort (and thus cost) is caused by setting up proper training data sets. However, models trained on specific data sets often perform unsatisfactorily when used to derive predictions for another (yet related) data set. We aim to overcome this problem by employing active learning to iteratively adapt an existing classifier to another domain. Precisely, we are concerned with semantic segmentation of 3D point clouds of multiple epochs. We first establish a Random Forest classifier for the first epoch of our data set and adapt it for successful prediction to two more temporally disjoint point clouds of the same but extended area. The point clouds, which are part of the newly introduced Hessigheim 3D benchmark data set, incorporate different characteristics with respect to the acquisition date and sensor configuration. We demonstrate that our workflow for domain adaptation is designed in such a way that it i) offers the possibility to greatly reduce labeling effort compared to a passive learning baseline or to an active learning baseline trained from scratch, if the domain gap is small enough and ii) at least does not cause more expenses (compared to a newly initialized active learning loop), if the domain gap is severe. The latter is especially beneficial in scenarios where the similarity of two different domains is hard to assess. Numéro de notice : A2022-435 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-259-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-259-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100743 [article]

Automatic interpretation of digital maps / Volker Walter in ISPRS Journal of photogrammetry and remote sensing, vol 66 n° 4 (July - August 2011)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 66 n° 4 (July - August 2011) . - pp 519 - 528 Titre : Automatic interpretation of digital maps Type de document : Article/Communication Auteurs : Volker Walter, Auteur ; F. Luo, Auteur Année de publication : 2011 Article en page(s) : pp 519 - 528 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification [Termes IGN] conception collaborative [Termes IGN] exploration de données géographiques [Termes IGN] interprétation automatique Résumé : (Auteur) In the past, the availability and/or the acquisition of spatial data were often the main problems of the realization of spatial applications. Meanwhile this situation has changed: on one hand, comprehensive spatial datasets already exist and on the other hand, new sensor technologies have the ability to capture fast and with high quality large amounts of spatial data. More and more responsible for the increasing accessibility of spatial data are also collaborative mapping techniques which enable users to create maps by themselves and to make them available in the internet. However, the potential of this diversity of spatial data can only hardly be utilized. Especially maps in the internet are represented very often only with graphical elements and no explicit information about the map’s scale, extension and content is available. Nevertheless, humans are able to extract this information and to interpret maps. For example, it is possible for a human to distinguish between rural and industrial areas only by looking at the objects’ geometries. Furthermore, a human can easily identify and group map objects that belong together. Also the type, scale and extension of a map can be identified under certain conditions only by looking at the objects’ geometries. All these examples can be subsumed under the term “map interpretation”. In this paper it is discussed how map interpretation can be automated and how automatic map interpretation can be used in order to support other processes. The different kinds of automatic map interpretation are discussed and two approaches are shown in detail. Numéro de notice : A2011-301 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2011.02.010 En ligne : https://doi.org/10.1016/j.isprsjprs.2011.02.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31080 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2011041	SL	Revue	Centre de documentation	Revues en salle	Disponible

Object-based evaluation of Lidar and multispectral data for automatic change detection in GIS databases / Volker Walter in GIS Geo-Informations-Systeme, vol 2005 n° 4 (April 2005)

Public [article]  inGIS Geo-Informations-Systeme > vol 2005 n° 4 (April 2005) . - pp 10 - 15 Titre : Object-based evaluation of Lidar and multispectral data for automatic change detection in GIS databases Type de document : Article/Communication Auteurs : Volker Walter, Auteur Année de publication : 2005 Article en page(s) : pp 10 - 15 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] analyse d'image orientée objet [Termes IGN] base de données localisées [Termes IGN] détection de changement [Termes IGN] données lidar [Termes IGN] image multibande [Termes IGN] photo-interprétation assistée par ordinateur [Termes IGN] qualité des données [Termes IGN] système d'information géographique Résumé : (Auteur) The automatic interpretation of aerial and satellites images is one of the main important research topics in photogrammetry and images analysis. The aim of the interpretation is the recognition or verification of objects in images. The quality of the interpretation results depends among other factors on the information content of the input data. The more information in the input data the easier is the interpretation process. In this paper an approach is described that increases the quality of the interpretation process by using existing GIS data as prior information on the one hand and by combining multispectral and LIDAR data on the other hand. The approach is used fo automatic change detection and is based on the evaluation of automatically derived training data sets from existing GIS data. For that reason no data dependent tuning factors have to be defined and no human interaction is necessary. Numéro de notice : A2005-249 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27385 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
058-05041	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Linking different geospatial databases by explicit relations / Steffen Volz in GIS Geo-Informations-Systeme, vol 2004 n° 9 (September 2004)

Public [article]  inGIS Geo-Informations-Systeme > vol 2004 n° 9 (September 2004) . - pp 16 - 23 Titre : Linking different geospatial databases by explicit relations Type de document : Article/Communication Auteurs : Steffen Volz, Auteur ; Volker Walter, Auteur Année de publication : 2004 Article en page(s) : pp 16 - 23 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes IGN] appariement topologique [Termes IGN] base de données localisées [Termes IGN] intégration de données [Termes IGN] ontologie [Termes IGN] représentation multiple Résumé : (Auteur) The growing awareness of the importance of spatial information has led to a continuously increasing demand for geospatial data. Thus, a lot of different companies and institutions have evolved that are aiming at satisfying this demand by capturing the real world according to the needs of different applications. This process involves that one and the same real world object is stored in several representations in different geospatial databases. The integration of these representations is a major research challenge in the field of GIS. In our approach we use a semi-automatic matching tool for defining relations between representations on the instance level. These relations are used in order to automatically derive an integrated data schema. The relations on the instance level as well as the integrated data schema can be used for automatically merging data sets, for automatically transferring updates from one data set into another or for a common analysis of spatial data from different sources. Numéro de notice : A2004-403 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26930 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
058-04091	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Object-based classification of remote sensing data for change detection / Volker Walter in ISPRS Journal of photogrammetry and remote sensing, vol 58 n° 3-4 (January - June 2004)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 58 n° 3-4 (January - June 2004) . - pp 225 - 238 Titre : Object-based classification of remote sensing data for change detection Type de document : Article/Communication Auteurs : Volker Walter, Auteur Année de publication : 2004 Article en page(s) : pp 225 - 238 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] base de données localisées [Termes IGN] classification automatique d'objets [Termes IGN] classification orientée objet [Termes IGN] classification par maximum de vraisemblance [Termes IGN] détection de changement [Termes IGN] fusion de données [Termes IGN] système d'information géographique Résumé : (Auteur) In this paper, a change detection approach based on an object-based classification of remote sensing data is introduced. The approach classifies not single pixels but groups of pixels that represent already existing objects in a GIS database. The approach is based on a supervised maximum likelihood classification. The multispectral bands grouped by objects and very different measures that can be derived from multispectral bands represent the n-dimensional feature space for the classification. The training areas are derived automatically from the geographical information system (GIS) database. After an introduction into the general approach, different input channels for the classification are defined and discussed. The results of a test on two test areas are presented. Afterwards, further measures, which can improve the result of the classification and enable the distinction between more land-use classes than with the introduced approach, are presented. Copyright ISPRS Numéro de notice : A2004-052 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2003.09.007 En ligne : https://doi.org/10.1016/j.isprsjprs.2003.09.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26580 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-04012	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-04011	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Classification of GIS-objects for change detection / Volker Walter in GIS Geo-Informations-Systeme, vol 2002 n° 12 (Dezember 2002)

Permalink

Automated update of ATKIS databases / Volker Walter in GIS Geo-Informations-Systeme, vol 13 n° 6 (Dezember 2000)

Permalink

Zuordnung von raumbezogenen Daten, am Beispiel der Datenmodelle ATKIS und GDF / Volker Walter (1997)  

Permalink