Centre dedocumentation
scientifique

Nonlocal graph convolutional networks for hyperspectral image classification / Lichao Mou in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 58 n° 12 (December 2020) . - pp 8246 - 8257 Titre : Nonlocal graph convolutional networks for hyperspectral image classification Type de document : Article/Communication Auteurs : Lichao Mou, Auteur ; Xiaoqiang Lu, Auteur ; Xuelong Li, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 8246 - 8257 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] classification semi-dirigée [Termes descripteurs IGN] entropie [Termes descripteurs IGN] graphe [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] réseau neuronal récurrent Résumé : (auteur) Over the past few years making use of deep networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), classifying hyperspectral images has progressed significantly and gained increasing attention. In spite of being successful, these networks need an adequate supply of labeled training instances for supervised learning, which, however, is quite costly to collect. On the other hand, unlabeled data can be accessed in almost arbitrary amounts. Hence it would be conceptually of great interest to explore networks that are able to exploit labeled and unlabeled data simultaneously for hyperspectral image classification. In this article, we propose a novel graph-based semisupervised network called nonlocal graph convolutional network (nonlocal GCN). Unlike existing CNNs and RNNs that receive pixels or patches of a hyperspectral image as inputs, this network takes the whole image (including both labeled and unlabeled data) in. More specifically, a nonlocal graph is first calculated. Given this graph representation, a couple of graph convolutional layers are used to extract features. Finally, the semisupervised learning of the network is done by using a cross-entropy error over all labeled instances. Note that the nonlocal GCN is end-to-end trainable. We demonstrate in extensive experiments that compared with state-of-the-art spectral classifiers and spectral–spatial classification networks, the nonlocal GCN is able to offer competitive results and high-quality classification maps (with fine boundaries and without noisy scattered points of misclassification). Numéro de notice : A2020-739 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2973363 date de publication en ligne : 12/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2973363 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96365 [article]

A graph convolutional network model for evaluating potential congestion spots based on local urban built environments / Kun Qin in Transactions in GIS, Vol 24 n° 5 (October 2020)  

Public [article]  inTransactions in GIS > Vol 24 n° 5 (October 2020) . - pp 1382-1401 Titre : A graph convolutional network model for evaluating potential congestion spots based on local urban built environments Type de document : Article/Communication Auteurs : Kun Qin, Auteur ; Yuanquan Xu, Auteur ; Chaogui Kang, Auteur ; Mei-Po Kwan, Auteur Année de publication : 2020 Article en page(s) : pp 1382-1401 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse spatio-temporelle [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection du bâti [Termes descripteurs IGN] données GPS [Termes descripteurs IGN] graphe [Termes descripteurs IGN] image Streetview [Termes descripteurs IGN] planification urbaine [Termes descripteurs IGN] point d'intérêt [Termes descripteurs IGN] taxi [Termes descripteurs IGN] trafic routier [Termes descripteurs IGN] Wuhan (Chine) [Termes descripteurs IGN] zone urbaine dense Résumé : (Auteur) Automatically identifying potential congestion spots in cities has significant practical implications for efficient urban development and management. It requires the ability to examine the relationships between urban built environment features and traffic congestion situations. This article presents a novel and effective approach for achieving the task based on a machine‐learning technique and publicly available street‐view imagery and point‐of‐interest (POI) data. The proposed multiple‐graph‐based convolutional network architecture can: (a) extract essential urban built environment features from street‐view imagery and neighboring POIs; (b) model the spatial dependencies between traffic congestion on road networks via graph convolution; and (c) evaluate the risk level of road intersections to emerging congestion situations based on local built environment features. We apply the model to Wuhan in China, and predict the potential congestion spots across the city. The results confirm that the model prediction is highly consistent (about 85.5%) when compared to the ground‐truth data based on traffic indices derived from a big taxi GPS trajectory dataset. This research enhances the understanding of traffic congestion situations under various geographic, societal, and economic contexts based on easily accessible road, street‐view, and POI datasets at large spatiotemporal scales. Numéro de notice : A2020-702 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12641 date de publication en ligne : 04/06/2020 En ligne : https://doi.org/10.1111/tgis.12641 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96225 [article]

Recognition of building group patterns using graph convolutional network / Rong Zhao in Cartography and Geographic Information Science, Vol 47 n° 5 (September 2020)  

Public [article]  inCartography and Geographic Information Science > Vol 47 n° 5 (September 2020) . - pp 400 - 417 Titre : Recognition of building group patterns using graph convolutional network Type de document : Article/Communication Auteurs : Rong Zhao, Auteur ; Tinghua Ai, Auteur ; Wenhao Yu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 400 - 417 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données topographiques [Termes descripteurs IGN] espace urbain [Termes descripteurs IGN] généralisation du bâti [Termes descripteurs IGN] graphe [Termes descripteurs IGN] modélisation du bâti [Termes descripteurs IGN] reconnaissance de formes Résumé : (auteur) Recognition of building group patterns is of great significance for understanding and modeling the urban space. However, many current methods cannot fully utilize spatial information and have trouble efficiently dealing with topographic data with high complexity. The design of intelligent computational models that can act directly on topographic data to extract spatial features is critical. To this end, we propose a novel deep neural network based on graph convolutions to automatically identify building group patterns with arbitrary forms. The method first models buildings by a general graph, and then the neural network simultaneously learns the structural information as well as vertex attributes to classify building objects. We apply this method to real building data, and the experimental results show that the proposed method can effectively capture spatial information to make more accurate predictions than traditional methods. Numéro de notice : A2020-510 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2020.1757512 date de publication en ligne : 12/06/2020 En ligne : https://doi.org/10.1080/15230406.2020.1757512 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95663 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2020051	SL	Revue	Centre de documentation	Revues en salle	Disponible

A semantic graph database for the interoperability of 3D GIS data / Eva Savina Malinverni in Applied geomatics, vol 12 n° 3 (September 2020)  

Public [article]  inApplied geomatics > vol 12 n° 3 (September 2020) . - 14 p. Titre : A semantic graph database for the interoperability of 3D GIS data Type de document : Article/Communication Auteurs : Eva Savina Malinverni, Auteur ; Berardo Naticchia, Auteur ; Jose Luis Lerma Garcia, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : 14 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes d'information géographique [Termes descripteurs IGN] base de données [Termes descripteurs IGN] bâtiment [Termes descripteurs IGN] CityGML [Termes descripteurs IGN] conservation de documents [Termes descripteurs IGN] données hétérogènes [Termes descripteurs IGN] graphe [Termes descripteurs IGN] indoorGML [Termes descripteurs IGN] interopérabilité sémantique [Termes descripteurs IGN] modélisation 3D [Termes descripteurs IGN] modélisation 3D du bâti BIM [Termes descripteurs IGN] ontologie [Termes descripteurs IGN] partage de données localisées [Termes descripteurs IGN] restauration de document [Termes descripteurs IGN] SIG 3D [Termes descripteurs IGN] stockage de données [Termes descripteurs IGN] web sémantique Résumé : (auteur) In the last decades, the use of information management systems in the building data processing led to radical changes to the methods of data production, documentation and archiving. In particular, the possibilities, given by these information systems, to visualize the 3D model and to formulate queries have placed the question of the information sharing in digital format. The integration of information systems represents an efficient solution for defining smart, sustainable and resilient projects, such as conservation and restoration processes, giving the possibilities to combine heterogeneous data. GIS provides a robust data storage system, a definition of topological and semantic relationships and spatial queries. 3D GIS makes possible the creation of three-dimensional model in a geospatial context. To promote the interoperability of GIS data, the present research aims first to analyse methods of conversion in CityGML and IndoorGML model, defining an ontological domain. This has led to the creation of a new enriched model, based on connections among the different elements of the urban model in GIS environment, and to the possibility to formulate queries based on these relations. The second step consists in collecting all data translated into a specific format that fill a graph database in a semantic web environment, while maintaining those relationships. The semantic web technology represents an efficient tool of interoperability that leaves open the possibility to import BIM data in the same graph database and to join both GIS and BIM models. The outcome will offer substantial benefits during the entire project life cycle. This methodology can also be applied to cultural heritage where the information management plays a key role. Numéro de notice : A2020-561 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12518-020-00334-3 date de publication en ligne : 24/08/2020 En ligne : https://doi.org/10.1007/s12518-020-00334-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95875 [article]

Learning sequential slice representation with an attention-embedding network for 3D shape recognition and retrieval in MLS point clouds / Zhipeng Luo in ISPRS Journal of photogrammetry and remote sensing, vol 161 (March 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 161 (March 2020) . - pp 147 - 163 Titre : Learning sequential slice representation with an attention-embedding network for 3D shape recognition and retrieval in MLS point clouds Type de document : Article/Communication Auteurs : Zhipeng Luo, Auteur ; Di Liu, Auteur ; Jonathan Li, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 147 - 163 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] balayage laser [Termes descripteurs IGN] données laser [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] graphe [Termes descripteurs IGN] reconnaissance de formes [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] réseau routier [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] télémétrie laser mobile Résumé : (Auteur) The representation of 3D data is the key issue for shape analysis. However, most of the existing representations suffer from high computational cost and structure information loss. This paper presents a novel sequential slice representation with an attention-embedding network, named RSSNet, for 3D point cloud recognition and retrieval in road environments. RSSNet has two main branches. Firstly, a sequential slice module is designed to map disordered 3D point clouds to ordered sequence of shallow feature vectors. A gated recurrent unit (GRU) module is applied to encode the spatial and content information of these sequential vectors. The second branch consists of a key-point based graph convolution network (GCN) with an embedding attention strategy to fuse the sequential and global features to refine the structure discriminability. Three datasets were used to evaluate the proposed method, one acquired by our mobile laser scanning (MLS) system and two public datasets (KITTI and Sydney Urban Objects). Experimental results indicated that the proposed method achieved better performance than recognition and retrieval state-of-the-art methods. RSSNet provided recognition rates of 98.08%, 95.77% and 70.83% for the above three datasets, respectively. For the retrieval task, RSSNet obtained excellent mAP values of 95.56%, 87.16% and 69.99% on three datasets, respectively. Numéro de notice : A2020-064 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.01.003 date de publication en ligne : 22/01/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.01.003 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94582 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020031	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020033	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020032	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Fast computation of distances in a tree / Marc Pierrot-Deseilligny (2020)    

Permalink

Knowledge graphs and big data processing / Valentina Janev (2020)  

Permalink

A space-time varying graph for modelling places and events in a network / Ikechukwu Maduako in International journal of geographical information science IJGIS, vol 33 n° 10 (October 2019)  

Permalink

Analysis of collaboration networks in OpenStreetMap through weighted social multigraph mining / Quy Thy Truong in International journal of geographical information science IJGIS, vol 33 n° 7 - 8 (July - August 2019)  

Permalink

Computing and querying strict, approximate, and metrically refined topological relations in linked geographic data / Blake Regalia in Transactions in GIS, vol 23 n° 3 (June 2019)  

Permalink

Deeply integrating linked data with geographic information systems / Gengchen Mai in Transactions in GIS, vol 23 n° 3 (June 2019)  

Permalink

Piecewise-planar approximation of large 3D data as graph-structured optimization / Stéphane Guinard in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2/W5 (May 2019)  

Permalink

Pairwise coarse registration of point clouds in urban scenes using voxel-based 4-planes congruent sets / Yusheng Xu in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Permalink

Central place indexing : hierarchical linear indexing systems for mixed-aperture hexagonal discrete global grid systems / Kevin Sahr in Cartographica, vol 54 n° 1 (spring 2019)  

Permalink

A graph-based approach for the structural analysis of road and building layouts / Mathieu Domingo in Geo-spatial Information Science, vol 22 n° 1 (March 2019)  

Permalink