Détail de l'auteur
Auteur Xin Chen |
Documents disponibles écrits par cet auteur (5)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
GA-Net: A geometry prior assisted neural network for road extraction / Xin Chen in International journal of applied Earth observation and geoinformation, vol 114 (November 2022)
[article]
Titre : GA-Net: A geometry prior assisted neural network for road extraction Type de document : Article/Communication Auteurs : Xin Chen, Auteur ; Qun Sun, Auteur ; Wenyue Guo, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 103004 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de contours
[Termes IGN] données multiéchelles
[Termes IGN] extraction automatique
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] extraction du réseau routier
[Termes IGN] jeu de données
[Termes IGN] Massachusetts (Etats-Unis)Résumé : (auteur) With geospatial intelligence research developing rapidly, automatic road extraction is becoming a fundamental and challenging task. Due to the special geometric structure and spectral information of road networks, existing methods suffer from incomplete and fractured results. In this work, a novel road extraction convolutional neural network, incorporating the road boundary details and road junction information via a dual-branch multi-task structure, is proposed to learn synergistic feature representations and strengthen road connectivity. Firstly, a BiFPN-based feature aggregation module is utilised to bridge the semantic gap between low-level and high-level feature maps, allowing multi-scale spatial details to be fully fused. Secondly, the boundary auxiliary branch, using a U-shaped network with a spatial-channel attention module, captures residential information for the backbone to enhance the subtleties of road edges. Thirdly, the node inferring branch models the road junction position jointly with the road surface, aiming to strengthen the topology structure and reduce the fragmented road segments. We perform experiments on three diverse road datasets, namely the DeepGlobe dataset, Massachusetts dataset, and SpaceNet dataset. The results demonstrate that our model shows an overall performance improvement over some SOTA algorithms and the IoU indicator achieves 3.86%, 0.79%, and 1.71% improvements over Unet on the three datasets, respectively. Numéro de notice : A2022-785 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.103004 En ligne : https://doi.org/10.1016/j.jag.2022.103004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101888
in International journal of applied Earth observation and geoinformation > vol 114 (November 2022) . - n° 103004[article]On enhanced PPP with single difference between-satellite ionospheric constraints / Yan Xiang in Navigation : journal of the Institute of navigation, vol 69 n° 1 (Spring 2022)
[article]
Titre : On enhanced PPP with single difference between-satellite ionospheric constraints Type de document : Article/Communication Auteurs : Yan Xiang, Auteur ; Xin Chen, Auteur ; Ling Pei, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 505 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] correction ionosphérique
[Termes IGN] modèle stochastique
[Termes IGN] positionnement ponctuel précis
[Termes IGN] retard ionosphèrique
[Termes IGN] simple différence
[Termes IGN] temps de convergenceRésumé : (auteur) Applications of precise point positioning (PPP) are limited by PPP’s long convergence time. One effective way to shorten the convergence time is to apply ionospheric constraints because of the external ionospheric information. The conventional way to do this is to apply high precision but biased ionospheric corrections. The limitations of the method are that all ionospheric constraints must be derived from the same set of reference stations to have the same data. An approach based on single differences between satellite ionospheric constraints (SDBS-IONO) is developed to address the data issue due to having no common satellite visibility. The proposed method is more flexible and scalable in terms of adding ionospheric constraints. Based on a network of about 130 stations, we validated the proposed SDBS-ION method and compared it to the conventional method. Our results confirm that the ionospheric constraints enhance the PPP convergence time significantly depending on the accuracy of ionospheric constraints. Finally, we discuss crucial factors regarding how long and accurate the effectiveness of ionospheric constraints are in reducing PPP convergence time. Numéro de notice : A2022-820 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.33012/navi.505 Date de publication en ligne : 07/11/2021 En ligne : https://doi.org/10.33012/navi.505 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101988
in Navigation : journal of the Institute of navigation > vol 69 n° 1 (Spring 2022) . - n° 505[article]A framework for annotating OpenStreetMap objects using geo-tagged tweets / Xin Chen in Geoinformatica, vol 22 n° 3 (July 2018)
[article]
Titre : A framework for annotating OpenStreetMap objects using geo-tagged tweets Type de document : Article/Communication Auteurs : Xin Chen, Auteur ; Hoang Vo, Auteur ; Yu Wang, Auteur ; Fusheng Wang, Auteur Année de publication : 2018 Article en page(s) : pp 589 - 613 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] corpus
[Termes IGN] données issues des réseaux sociaux
[Termes IGN] données localisées des bénévoles
[Termes IGN] enrichissement sémantique
[Termes IGN] géobalise
[Termes IGN] intégration de données
[Termes IGN] objet géographique
[Termes IGN] OpenStreetMap
[Termes IGN] TwitterRésumé : (Auteur) Recent years have witnessed an explosion of geospatial data, especially in the form of Volunteered Geographic Information (VGI). As a prominent example, OpenStreetMap (OSM) creates a free editable map of the world from a large number of contributors. On the other hand, social media platforms such as Twitter or Instagram supply dynamic social feeds at population level. As much of such data is geo-tagged, there is a high potential on integrating social media with OSM to enrich OSM with semantic annotations, which will complement existing objective description oriented annotations to provide a broader range of annotations. In this paper, we propose a comprehensive framework on integrating social media data and VGI data to derive knowledge about geographical objects, specifically, top relevant annotations from tweets for objects in OSM. We first integrate geo-tagged tweets with OSM data with scalable spatial queries running on MapReduce. We propose a frequency based method for annotating boundary based geographic objects (a polygon), and a probability based method for annotating point based geographic objects (Latitude and Longitude), with consideration of noise. We evaluate our methods using a large geo-tagged tweets corpus and representative geographic objects from OSM, which demonstrates promising results through ground-truth comparison and case studies. We are able to produce up to 80% correct names for geographical objects and discover implicitly relevant information, such as popular exhibitions of a museum, the nicknames or visitors’ impression to a tourism attraction. Numéro de notice : A2018-369 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10707-018-0323-8 Date de publication en ligne : 20/06/2018 En ligne : https://doi.org/10.1007/s10707-018-0323-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90760
in Geoinformatica > vol 22 n° 3 (July 2018) . - pp 589 - 613[article]vol 20 n° 2 - April - June 2016 - Special Section on Current Computational Transportation Science (Bulletin de Geoinformatica) / Stephan Winter
[n° ou bulletin]
est un bulletin de Geomatica / Canadian institute of geomatics = Association canadienne des sciences géomatiques (Canada) (1993 -)
Titre : vol 20 n° 2 - April - June 2016 - Special Section on Current Computational Transportation Science Type de document : Périodique Auteurs : Stephan Winter, Éditeur scientifique ; Xin Chen, Éditeur scientifique ; Bo Xu, Auteur Année de publication : 2016 Langues : Anglais (eng) Numéro de notice : sans Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Numéro de périodique En ligne : http://link.springer.com/journal/10707/20/2/page/1 Format de la ressource électronique : URL sommaire Permalink : https://documentation.ensg.eu/index.php?lvl=bulletin_display&id=26607 [n° ou bulletin]Contient
- Towards fusing uncertain location data from heterogeneous sources / Bing Zhang in Geoinformatica, vol 20 n° 2 (April - June 2016)
- Towards sustainable mobility behavior: research challenges for location-aware information and communication technology / Paul Weiser in Geoinformatica, vol 20 n° 2 (April - June 2016)
- Advanced methods for the estimation of an unknown projection from a map / Tomáš Bayer in Geoinformatica, vol 20 n° 2 (April - June 2016)
- A framework for intelligence analysis using spatio-temporal storytelling / Raimundo F. Dos Santos Jr. in Geoinformatica, vol 20 n° 2 (April - June 2016)
- Exploring cell tower data dumps for supervised learning-based point-of-interest prediction (industrial paper) / Ran Wang in Geoinformatica, vol 20 n° 2 (April - June 2016)
Titre : Relative laser scanner and image pose estimation from points and segments Type de document : Article/Communication Auteurs : Matthieu Deveau , Auteur ; Nicolas Paparoditis , Auteur ; Marc Pierrot-Deseilligny , Auteur ; Xin Chen, Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2004 Collection : International Archives of Photogrammetry and Remote Sensing, ISSN 0252-8231 num. 35-B3 Conférence : ISPRS 2004, 20th international congress of photogrammetry and remote sensing, Geo-Imagery Bridging continents 12/07/2004 23/07/2004 Istanbul Turquie OA ISPRS Archives Importance : pp 1130 - 1135 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] contrainte géométrique
[Termes IGN] détection de contours
[Termes IGN] données laser
[Termes IGN] métrologie
[Termes IGN] position directe
[Termes IGN] primitive géométrique
[Termes IGN] segment de droite
[Termes IGN] semis de pointsIndex. décimale : 33.30 Photogrammétrie numérique Résumé : (Auteur) This paper presents an approach involving linear features for pose estimation. Here we are interesting in surveys mixing image and laser scanning, for metrological applications. Since data need to be registered with the best accuracy, we are faced to a 2D-3D pose estimation problem. In most cases, scenes contain numerous segments, which are good orientation dues. We use these segments to find pose. Therefore, targets are less prevalent for location and orientation estimation purpose. This means less field operations during data acquisition. Since some scenes with very few straight lines can leave insufficient spatial constraints, we reintroduce points. We can deal with feature points to reinforce the System. Then, the algorithm simultaneously minimizes an energy function managing distances between 3D points projection in images and image points, and distances on segments ends. Precise determination of primitives in 2D and 3D data leads to fine orientation. Using subpixelar regression after an edge detection gives high-quality estimates for 2D segments. In point clouds, 3D segments corne from plane intersection. We discuss relative influence of features through uncertainty assessment. Numéro de notice : 57399 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.isprs.org/proceedings/XXXV/congress/comm3/papers/436.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=64739 Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 57399-01 33.30 Tiré à part Centre de documentation Photogrammétrie - Lasergrammétrie Disponible