Centre de documentation
scientifique

Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning / Junwei Han in IEEE Transactions on geoscience and remote sensing, vol 53 n° 6 (June 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 6 (June 2015) . - pp 3325 - 3337 Titre : Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning Type de document : Article/Communication Auteurs : Junwei Han, Auteur ; Dingwen Zhang, Auteur ; Gong Cheng, Auteur Année de publication : 2015 Article en page(s) : pp 3325 - 3337 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage semi-dirigé [Termes IGN] détection d'objet [Termes IGN] estimation bayesienne [Termes IGN] état de l'art [Termes IGN] moteur d'inférence Résumé : (Auteur) The abundant spatial and contextual information provided by the advanced remote sensing technology has facilitated subsequent automatic interpretation of the optical remote sensing images (RSIs). In this paper, a novel and effective geospatial object detection framework is proposed by combining the weakly supervised learning (WSL) and high-level feature learning. First, deep Boltzmann machine is adopted to infer the spatial and structural information encoded in the low-level and middle-level features to effectively describe objects in optical RSIs. Then, a novel WSL approach is presented to object detection where the training sets require only binary labels indicating whether an image contains the target object or not. Based on the learnt high-level features, it jointly integrates saliency, intraclass compactness, and interclass separability in a Bayesian framework to initialize a set of training examples from weakly labeled images and start iterative learning of the object detector. A novel evaluation criterion is also developed to detect model drift and cease the iterative learning. Comprehensive experiments on three optical RSI data sets have demonstrated the efficacy of the proposed approach in benchmarking with several state-of-the-art supervised-learning-based object detection approaches. Numéro de notice : A2015 - 283 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2374218 Date de publication en ligne : 18/12/2014 En ligne : https://doi.org/10.1109/TGRS.2014.2374218 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76400 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015061	SL	Revue	Centre de documentation	Revues en salle	Disponible

An inference-based framework to manage data provenance in geoscience applications / Mohammad Rezwanul Huq in IEEE Transactions on geoscience and remote sensing, vol 51 n° 11 (November 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 11 (November 2013) . - pp 5113 - 5130 Titre : An inference-based framework to manage data provenance in geoscience applications Type de document : Article/Communication Auteurs : Mohammad Rezwanul Huq, Auteur ; Peter M.G. Apers, Auteur ; Andreas Wombacher, Auteur Année de publication : 2013 Article en page(s) : pp 5113 - 5130 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Infrastructure de données [Termes IGN] flux de travaux [Termes IGN] inférence [Termes IGN] moteur d'inférence [Termes IGN] source de données [Termes IGN] synergiciel [Termes IGN] traitement de données localisées Résumé : (Auteur) Data provenance allows scientists to validate their model as well as to investigate the origin of an unexpected value. Furthermore, it can be used as a replication recipe for output data products. However, capturing provenance requires enormous effort by scientists in terms of time and training. First, they need to design the workflow of the scientific model, i.e., workflow provenance, which requires both time and training. However, in practice, scientists may not document any workflow provenance before the model execution due to the lack of time and training. Second, they need to capture provenance while the model is running, i.e., fine-grained data provenance. Explicit documentation of fine-grained provenance is not feasible because of the massive storage consumption by provenance data in the applications, including those from the geoscience domain where data are continuously arriving and are processed. In this paper, we propose an inference-based framework, which provides both workflow and fine-grained data provenance at a minimal cost in terms of time, training, and disk consumption. Our proposed framework is applicable to any given scientific model, and is capable of handling different model dynamics, such as variation in the processing time as well as input data products arrival pattern. Our evaluation of the framework in a real use case with geospatial data shows that the proposed framework is relevant and suitable for scientists in geoscientific domain. Numéro de notice : A2013-613 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2013.2247769 En ligne : https://doi.org/10.1109/TGRS.2013.2247769 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32749 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013111	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Automatic reasoning for geometric constraints in 3D city models with uncertain observations / S. Loch-Dehbi in ISPRS Journal of photogrammetry and remote sensing, vol 66 n° 2 (March - April 2011)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 66 n° 2 (March - April 2011) . - pp 177 - 187 Titre : Automatic reasoning for geometric constraints in 3D city models with uncertain observations Type de document : Article/Communication Auteurs : S. Loch-Dehbi, Auteur ; L. Plumer, Auteur Année de publication : 2011 Article en page(s) : pp 177 - 187 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] contrainte géométrique [Termes IGN] géométrie projective [Termes IGN] hauteur du bâti [Termes IGN] incertitude géométrique [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modélisation 3D [Termes IGN] moteur d'inférence [Termes IGN] Ploynôme [Termes IGN] programmation par contraintes [Termes IGN] reconstruction 3D du bâti [Termes IGN] semis de points Résumé : (Auteur) This paper presents a novel approach to automated geometric reasoning for 3D building models. Geometric constraints like orthogonality or parallelity play a prominent role in man-made objects such as buildings. Thus, constraint based modelling, that specifies buildings by their individual components and the constraints between them, is a common approach in 3D city models. Since prototyped building models allow one to incorporate a priori knowledge they support the 3D reconstruction of buildings from point clouds and allow the construction of virtual cities. However, high level building models have a high degree of complexity and consequently are not easily manageable. Interactive tools are needed which facilitate the development of consistent models that, for instance, do not entail internal logical contradictions. Furthermore, there is often an interest in a compact, redundancy-free representation. We propose an approach that uses algebraic methods to prove that a constraint is deducible from a set of premises. While automated reasoning in 2D models is practical, a substantial increase in complexity can be observed in the transition to the three-dimensional space. Apart from that, algebraic theorem provers are restricted to crisp constraints so far. Thus, they are unable to handle quality issues, which are, however, an important aspect of GIS data and models. In this article we present an approach to automatic 3D reasoning which explicitly addresses uncertainty. Hereby, our aim is to support the interactive modelling of 3D city models and the automatic reconstruction of buildings. Geometric constraints are represented by multivariate polynomials whereas algebraic reasoning is based on Wu’s method of pseudodivision and characteristic sets. The reasoning process is further supported by logical inference rules. In order to cope with uncertainty and to address quality issues the reasoner integrates uncertain projective geometry and statistical hypothesis tests. Consequently, it allows one to derive uncertain conclusions from uncertain premises. The quality of such conclusions is quantified in a way which is sound both from a logical and a statistical perspective. Numéro de notice : A2011-071 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2010.12.003 En ligne : https://doi.org/10.1016/j.isprsjprs.2010.12.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30852 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2011021	SL	Revue	Centre de documentation	Revues en salle	Disponible

Generation and application of rules for quality dependent facade reconstruction / S. Becker in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 6 (November - December 2009)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 64 n° 6 (November - December 2009) . - 14 p. ; pp 640 - 653 Titre : Generation and application of rules for quality dependent facade reconstruction Type de document : Article/Communication Auteurs : S. Becker, Auteur Année de publication : 2009 Article en page(s) : 14 p. ; pp 640 - 653 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] architecture urbaine [Termes IGN] base de règles [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] façade [Termes IGN] grammaire de graphes [Termes IGN] itération [Termes IGN] lasergrammétrie [Termes IGN] moteur d'inférence [Termes IGN] photo-interprétation assistée par ordinateur [Termes IGN] qualité des données [Termes IGN] reconstruction 3D du bâti Résumé : (Auteur) Frequently, terrestrial LiDAR and image data are used to extract high resolution building geometry like windows, doors and protrusions for three-dimensional (3D) façade reconstruction. However, such a purely data driven bottom-up modelling of façade structures is only feasible if the available observations meet considerable requirements on data quality. Errors in measurement, varying point densities, reduced accuracies, as well as incomplete coverage affect the achievable correctness and reliability of the reconstruction result. While dependence on data quality is a general disadvantage with data driven bottom-up approaches, model based top-down reconstructions are much more robust. Algorithms introduce knowledge about the appearance and arrangement of objects. Thus, they cope with data uncertainty and allow for a procedural modelling of building structures in a predefined architectural style, which is inherent in grammar or model descriptions. We aim at a quality sensitive façade reconstruction which is on the one hand robust against erroneous and incomplete data, but on the other hand not subject to prespecified rules or models. For this purpose, we combine bottom-up and top-down strategies by integrating automatically inferred rules into a data driven reconstruction process. Façade models reconstructed during a bottom-up method serve as a knowledge base for further processing. Dominant or repetitive features and regularities as well as their hierarchical relationship are detected from the modelled façade elements and automatically translated into rules. These rules together with the 3D representations of the modelled façade elements constitute a formal grammar. It holds all the information which is necessary to reconstruct façades in the style of the given building. The paper demonstrates that the proposed algorithm is very flexible towards different data quality and incomplete sensor data. The inferred grammar is used for the verification of the façade model produced during the data driven reconstruction process and the generation of synthetic façades for which only partial or no sensor data is available. Moreover, knowledge propagation is not restricted to façades of one single building. Based on a small set of formal grammars derived from just a few observed buildings, façade reconstruction is also possible for whole districts featuring uniform architectural styles. Copyright 2009 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Numéro de notice : A2009-496 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2009.06.002 En ligne : https://doi.org/10.1016/j.isprsjprs.2009.06.002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30125 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-09061	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Fuzzy inference guided cellular automata urban-growth modelling using multi-temporal satellite images / S. Al-Kheder in International journal of geographical information science IJGIS, vol 22 n°11-12 (november 2008)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 22 n°11-12 (november 2008) . - pp 1271 - 1293 Titre : Fuzzy inference guided cellular automata urban-growth modelling using multi-temporal satellite images Type de document : Article/Communication Auteurs : S. Al-Kheder, Auteur ; Jing Wang, Auteur ; J. Shan, Auteur Année de publication : 2008 Article en page(s) : pp 1271 - 1293 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse diachronique [Termes IGN] automate cellulaire [Termes IGN] croissance urbaine [Termes IGN] étalonnage des données [Termes IGN] image multitemporelle [Termes IGN] image satellite [Termes IGN] Indianapolis [Termes IGN] Inférence floue [Termes IGN] modélisation spatio-temporelle [Termes IGN] moteur d'inférence [Termes IGN] urbanisation Résumé : (Auteur) This paper presents a fuzzy inference guided cellular automata approach. Semantic or linguistic knowledge on urban development is expressed as fuzzy rules, based on which fuzzy inference is applied to determine the urban development potential for each pixel. A defuzzification process converts the development potential to the required neighbourhood development level, which is taken by cellular automata as initial approximation for its transition rules. Such approximations are updated through spatial calibration over townships and temporal calibration with multi-temporal satellite images. Assessment of the modelling results is based on three evaluation measures: fitness and Type I and Type II errors. The approach is applied to model the growth of the city of Indianapolis, Indiana over a period of 30 years from 1973 to 2003. A fitness level of 100 + 20% with 30% average errors can be achieved for 80% of the townships in urban-growth prediction. Copyright Taylor & Francis Numéro de notice : A2008-403 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/13658810701617292 En ligne : https://doi.org/10.1080/13658810701617292 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29395 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-08071	RAB	Revue	Centre de documentation	En réserve L003	Disponible
079-08072	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Cartographic generalization of roads in a local and adaptive approach: A knowledge acquistion problem / Sébastien Mustière in International journal of geographical information science IJGIS, vol 19 n° 8 - 9 (september 2005)  

Permalink

Photogrammétrie et archéologie sous-marine profonde : le cas de l'épave étrusque grand Ribaud F [2ème partie] / P. Drap in XYZ, n° 104 (septembre - novembre 2005)

Permalink

Integrating knowledge representation and reasoning in geographical information systems / P. Mancarella in International journal of geographical information science IJGIS, vol 18 n° 4 (june 2004)  

Permalink

Regelbasierte Interpretation unstrukturierter Vektorkarten / M. Weindorf (2002)

Permalink

Données géographiques et raisonnement / D. Saint-Joan (1995)

Permalink

Représentation des connaissances pour la mise à jour automatique des Systèmes d'Information Géographique par photos aériennes / Carlo Schenone (1994)

Permalink

Recherches dans le domaine de l'intelligence artificielle et systèmes experts en géographie / V.S. Tikunov in Annales de géographie, n° 552 (mars - avril 1990)  

Permalink

Méthodologie de conception d'un système expert pour la généralisation cartographique / Xiao Chun Boury-Zhao (1990)  

Permalink

Automatisation de problèmes de positionnement [de toponymes] sous contraintes / Pierre Titeux (1989)

Permalink

Kirk, un environnement de développement de systèmes experts : une application, l'interprétation de photographies aériennes / W. Chehire (30/05/1988)

Permalink