Centre de documentation
scientifique

Semi-supervised label propagation for multi-source remote sensing image change detection / Fan Hao in Computers & geosciences, vol 170 (January 2023)  

Public [article]  inComputers & geosciences > vol 170 (January 2023) . - n° 105249 Titre : Semi-supervised label propagation for multi-source remote sensing image change detection Type de document : Article/Communication Auteurs : Fan Hao, Auteur ; Zong-Fang Ma, Auteur ; Hong Peng Tian, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 105249 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] classification barycentrique [Termes IGN] classification pixellaire [Termes IGN] détection de changement [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] étiquette [Termes IGN] filtrage du bruit [Termes IGN] image multi sources Résumé : (auteur) Remote sensing image change detection remains a challenging task. Most existing approaches are based on fully supervised learning, but labeled data are so scarce for change detection. It is difficult to exhibit high detection performance with a limited amount of labeled data. In this paper, we propose a semi-supervised Label Propagation (SSLP) approach for multi-source remote sensing image change detection. First, a clustering label propagation (CLP) method is designed to cluster pre and post images, respectively, and assign pseudo labels to unlabeled pixel pairs that have similar mapping relationships to labeled pixel pairs. Second, a pixel density metric is investigated to filter out the data with low density and retain the data with high density, which can ensure the reliability of the propagated data. Third, a secondary expansion method based on pixel neighborhood is used to generate enough training data for training a classifier. Finally, the effectiveness of SSLP is validated on three real datasets by comparing to other related methods. Numéro de notice : A2023-032 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.cageo.2022.105249 Date de publication en ligne : 19/10/2022 En ligne : https://doi.org/10.1016/j.cageo.2022.105249 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102292 [article]

Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images / Ekrem Saralioglu in Geocarto international, vol 37 n° 18 ([01/09/2022])  

Public [article]  inGeocarto international > vol 37 n° 18 [01/09/2022] . - pp 5433 - 5452 Titre : Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images Type de document : Article/Communication Auteurs : Ekrem Saralioglu, Auteur ; Oguz Gungor, Auteur Année de publication : 2022 Article en page(s) : pp 5433 - 5452 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] acquisition d'images [Termes IGN] apprentissage profond [Termes IGN] approche participative [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couleur (variable spectrale) [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] étiquette [Termes IGN] image multibande [Termes IGN] OpenStreetMap [Termes IGN] pixel [Termes IGN] plateforme collaborative [Termes IGN] texture d'image [Termes IGN] Worldview Résumé : (auteur) In order to solve insufficient training data problem in remote sensing, a web platform was created so that registered users can generate labeled data for various classes in a dynamic structure. Users were asked to select representative pixel groups for the forest, hazelnut, shadow, soil, tea, and building classes with the polygon tool, and then assign a class label corresponding to each created polygon thanks to the help document displaying descriptive information regarding the locations, colors, textures and distributions of the classes in the image. Crowdsourcing was again used to test the accuracy of the tagged data produced by crowdsourcing. The created data set was overlaid with the original WV-2 image, and the correctness of the labels ​​of the polygons was once visually verified. Finally, the WV-2 image, consisting of 40 patches, was classified with CNN and an average of over 95% accuracy was achieved. Numéro de notice : A2022-702 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1917006 Date de publication en ligne : 26/05/2021 En ligne : https://doi.org/10.1080/10106049.2021.1917006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101561 [article]

The effect of map label language on the visual search of cartographic point symbols / Paweł Cybulski in Cartography and Geographic Information Science, vol 49 n° 3 (May 2022)  

Public [article]  inCartography and Geographic Information Science > vol 49 n° 3 (May 2022) . - pp 189 - 204 Titre : The effect of map label language on the visual search of cartographic point symbols Type de document : Article/Communication Auteurs : Paweł Cybulski, Auteur ; Vassilios Krassanakis, Auteur Année de publication : 2022 Article en page(s) : pp 189 - 204 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] détection de cible [Termes IGN] étiquette [Termes IGN] langage cartographique [Termes IGN] langue [Termes IGN] lecture de carte [Termes IGN] oculométrie [Termes IGN] sémiologie graphique [Termes IGN] symbole graphique [Termes IGN] visualisation cartographique [Vedettes matières IGN] Cartologie Résumé : (auteur) The present study aims to examine how the visual search for cartographic symbols is affected by the language of map labels. More specifically, we explore the influence of native language in the performance of a visual search map task which is referred to target point symbol detection. The main research hypothesis is that the relative position of the target symbols plays a significant role in the visual search process, although labels language impacts reaction time. In a controlled laboratory experiment with 38 participants and eye tracking technology, we used maps with labels in participants’ native language (Polish) and in Chinese, which participants could neither read nor write. We find that the detection of target symbols with Chinese labels is faster when the symbol’s location is peripheral. On the other hand, faster detection of target symbols with labels in participants’ native language favors central location. It turned out that having noticed the target symbol, participants fixated on the native language label. For Chinese labels, having seen the target symbol, participants did not fixate on the label. It also turned out that when participants searched for a target symbol located in the peripheral zone, more visual attention was in this zone. However, when the target symbol’s location was central, the participants’ visual attention focused mostly on the central zone. This confirms the significant role of the location of cartographic symbols in the visual search process. Numéro de notice : A2022- 292 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2021.2007419 Date de publication en ligne : 16/12/2021 En ligne : https://doi.org/10.1080/15230406.2021.2007419 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100340 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2022031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Discovering transition patterns among OpenStreetMap feature classes based on the Louvain method / Yijiang Zhao in Transactions in GIS, vol 26 n° 1 (February 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 1 (February 2022) . - pp 236 - 258 Titre : Discovering transition patterns among OpenStreetMap feature classes based on the Louvain method Type de document : Article/Communication Auteurs : Yijiang Zhao, Auteur ; Wentao Yang, Auteur ; Yizhi Liu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 236 - 258 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] Açores, archipel des [Termes IGN] algorithme glouton [Termes IGN] données localisées des bénévoles [Termes IGN] étiquette [Termes IGN] géobalise [Termes IGN] Indiana (Etats-Unis) [Termes IGN] OpenStreetMap [Termes IGN] réseau routier Résumé : (auteur) Numerous studies have shown that OpenStreetMap (OSM) data can achieve high positional quality. However, the thematic attributes of OSM objects can be modified several times, which has a large impact on semantic heterogeneity. Identifying transition patterns within OSM feature classes is an important preliminary step for the tag recommendation algorithm, which can reduce the number of modifications and enhance the efficiency of OSM data updates. In this article, we propose an approach for discovering transition patterns among OSM feature classes. We first produced the transition matrix of feature classes and then developed a graph. Next, the Louvain method for community detection was utilized to cluster the feature classes. OSM data from Indiana, USA, and the Azores, Portugal, were used for our experiments. Some transition patterns were discovered: (1) many feature classes with the most transitions are the same in both datasets and most transitions occur in road-related feature classes; (2) people tend to tag general classes if they are unsure of the specific classes of tagged objects; and (3) most class transitions occurred as a result of volunteers improving the specificity and precision of feature classes. Moreover, consistently confusing concept pairs were identified. Numéro de notice : A2022-178 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12843 Date de publication en ligne : 08/10/2021 En ligne : https://doi.org/10.1111/tgis.12843 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99835 [article]

Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances / Xiaomeng Wu in International journal of computer vision, vol 126 n° 7 (July 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 7 (July 2018) . - pp 689 - 713 Titre : Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances Type de document : Article/Communication Auteurs : Xiaomeng Wu, Auteur ; Kaoru Hiramatsu, Auteur ; Kunio Kashino, Auteur Année de publication : 2018 Article en page(s) : pp 689 - 713 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] étiquette [Termes IGN] instance [Termes IGN] méthode robuste [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] relation spatiale Résumé : (Auteur) Spatial verification methods permit geometrically stable image matching, but still involve a difficult trade-off between robustness as regards incorrect rejection of true correspondences and discriminative power in terms of mismatches. To address this issue, we ask whether an ensemble of weak geometric constraints that correlates with visual similarity only slightly better than a bag-of-visual-words model performs better than a single strong constraint. We consider a family of spatial verification methods and decompose them into fundamental constraints imposed on pairs of feature correspondences. Encompassing such constraints leads us to propose a new method, which takes the best of existing techniques and functions as a unified Ensemble of pAirwise GEometric Relations (EAGER), in terms of both spatial contexts and between-image transformations. We also introduce a novel and robust reranking method, in which the object instances localized by EAGER in high-ranked database images are reissued as new queries. EAGER is extended to develop a smoothness constraint where the similarity between the optimized ranking scores of two instances should be maximally consistent with their geometrically constrained similarity. Reranking is newly formulated as two label propagation problems: one is to assess the confidence of new queries and the other to aggregate new independently executed retrievals. Extensive experiments conducted on four datasets show that EAGER and our reranking method outperform most of their state-of-the-art counterparts, especially when large-scale visual vocabularies are used. Numéro de notice : A2018-411 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1063-9 Date de publication en ligne : 31/01/2018 En ligne : https://doi.org/10.1007/s11263-018-1063-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90886 [article]

Mixed map labeling / Maarten Löffler in Journal of Spatial Information Science, JoSIS, n° 13 (September 2016)  

Permalink

Génération de modèles numériques de surface et détection de changements 3D à partir d'imagerie satellite stéréoscopique très haute résolution / Cyrielle Guerin (2014)  

Permalink

Finding science with science: Evaluating a domain and scientific ontology user interface for the discovery of scientific resources / Kristin Stock in Transactions in GIS, vol 17 n° 4 (August 2013)  

Permalink

vol 16 n° 4 - juillet - août 2011 - Système d'information mobiquitaires (Bulletin de Ingénierie des systèmes d'information, ISI : Revue des sciences et technologies de l'information, RSTI) / Serge Miranda  

Permalink

Utilisation de sites Web, (Wikipedia, Flickr, Google) pour caractériser des objets géographiques / Léa Massiot (2010)

Permalink