Centre dedocumentation
scientifique

Effective triplet mining improves training of multi-scale pooled CNN for image retrieval / Federico Vaccaro in Machine Vision and Applications, vol 33 n° 1 (January 2022)  

Public [article]  inMachine Vision and Applications > vol 33 n° 1 (January 2022) . - n° 16 Titre : Effective triplet mining improves training of multi-scale pooled CNN for image retrieval Type de document : Article/Communication Auteurs : Federico Vaccaro, Auteur ; Marco Bertini, Auteur ; Tiberio Uricchio, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 16 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] agrégation [Termes IGN] analyse visuelle [Termes IGN] architecture de réseau [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] exploration de données [Termes IGN] extraction de traits caractéristiques [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] réseau neuronal siamois [Termes IGN] triplet Résumé : (auteur) In this paper, we address the problem of content-based image retrieval (CBIR) by learning images representations based on the activations of a Convolutional Neural Network. We propose an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on the trainable aggregation layer NetVLAD (Arandjelovic et al in Proceedings of the IEEE conference on computer vision and pattern recognition CVPR, NetVLAD, 2016) and bags of local features obtained by splitting the activations, allowing to reduce the dimensionality of the descriptor and to increase the performance of retrieval. Training is performed using an improved triplet mining procedure that selects samples based on their difficulty to obtain an effective image representation, reducing the risk of overfitting and loss of generalization. Extensive experiments show that our approach, that can be effectively used with different CNN architectures, obtains state-of-the-art results on standard and challenging CBIR datasets. Numéro de notice : A2022-237 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01260-z Date de publication en ligne : 06/01/2022 En ligne : https://doi.org/10.1007/s00138-021-01260-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100153 [article]

La géovisualisation de données massives sur le Web : entre avancées technologiques et évolutions cartographiques / Boris Mericskay in Mappemonde [en ligne], n° 131 (juillet 2021)  

Public [article]  inMappemonde [en ligne] > n° 131 (juillet 2021) . - n° 5595 Titre : La géovisualisation de données massives sur le Web : entre avancées technologiques et évolutions cartographiques Type de document : Article/Communication Auteurs : Boris Mericskay, Auteur Année de publication : 2021 Article en page(s) : n° 5595 Note générale : bibliographie Langues : Français (fre) Descripteur : [Termes IGN] 3D Tiles [Termes IGN] agrégation [Termes IGN] cartographie des flux [Termes IGN] dalle [Termes IGN] données localisées 3D [Termes IGN] données massives [Termes IGN] données vectorielles [Termes IGN] interactivité [Termes IGN] représentation continue [Termes IGN] représentation discrète [Termes IGN] visualisation 3D [Termes IGN] vue immersive [Termes IGN] webGL [Vedettes matières IGN] Géovisualisation Résumé : (auteur) Les avancées techniques autour de la visualisation de données volumineuses et l’affichage en 3D au sein de navigateurs Web viennent renouveler les pratiques de géovisualisation. Des modes basés sur l’agrégation à l’extrusion 3D en passant par les fonds de cartes personnalisés, le visage des cartes en ligne se transforme. Afin de bien comprendre cette forme de cartographie émergente et les enjeux sous-jacents, cet article questionne les logiques et les modes de représentation cartographique des données volumineuses qui prennent forme sur le Web au prisme des technologies émergentes et des usages associés. Numéro de notice : A2021-603 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : 10.4000/mappemonde.5595 En ligne : https://doi.org/10.4000/mappemonde.5595 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98341 [article]

Forest fragmentation assessment using field-based sampling data from forest inventories / Habib Ramezani in Scandinavian journal of forest research, vol 36 n° 4 ([01/05/2021])  

Public [article]  inScandinavian journal of forest research > vol 36 n° 4 [01/05/2021] . - pp 289 - 296 Titre : Forest fragmentation assessment using field-based sampling data from forest inventories Type de document : Article/Communication Auteurs : Habib Ramezani, Auteur ; Alireza Ramezani, Auteur Année de publication : 2021 Article en page(s) : pp 289 - 296 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] agrégation [Termes IGN] corridor biologique [Termes IGN] distance euclidienne [Termes IGN] échantillonnage [Termes IGN] inventaire forestier étranger (données) [Termes IGN] Suède [Termes IGN] surveillance forestière [Termes IGN] variance [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Forest fragmentation has a relevant impact on biodiversity. An interesting alternative to estimate these indices is to use sampling data. This study aims to estimate aggregation index (AI) and the degree of clumping of forested landscape based on AI. The assessment was conducted using different point distances, inventory regions and cardinal directions. For this purpose, a dataset from one five-year periods (2007–2011) of the Swedish National Forest Inventory (NFI) was used. The estimation of AI from field-based inventory can give us a general picture of the current status of forest landscape. The results also show that the estimated AI is a distance dependent function. The corresponding estimated variance of the index is smaller for longer distances. The obtained results indicate that the estimated variance depends on both sample size and pair point distances. Estimated AI showed different values in different cardinal directions. To compare two regions or a given region over time, a given point distance should be used. The main advantage of the applied procedure is that a range of AI values can be produced rather than a single number. Furthermore, in field-based inventory, the obtained results are more reliable, because one works implicitly with a single forest definition only. Numéro de notice : A2021-605 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET Nature : Article DOI : 10.1080/02827581.2021.1908592 En ligne : https://doi.org/10.1080/02827581.2021.1908592 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98331 [article]

Discriminant analysis for lodging severity classification in wheat using RADARSAT-2 and Sentinel-1 data / Sugandh Chauhan in ISPRS Journal of photogrammetry and remote sensing, vol 164 (June 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 164 (June 2020) . - pp 138 - 151 Titre : Discriminant analysis for lodging severity classification in wheat using RADARSAT-2 and Sentinel-1 data Type de document : Article/Communication Auteurs : Sugandh Chauhan, Auteur ; Roshanak Darvishzadeh, Auteur ; Mirco Boschetti, Auteur ; Andrew Nelson, Auteur Année de publication : 2020 Article en page(s) : pp 138 - 151 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] agrégation [Termes IGN] analyse diachronique [Termes IGN] analyse discriminante [Termes IGN] blé (céréale) [Termes IGN] courbure [Termes IGN] gestion prévisionnelle [Termes IGN] image Radarsat [Termes IGN] image Sentinel-SAR [Termes IGN] Italie [Termes IGN] matrice de confusion [Termes IGN] méthode des moindres carrés [Termes IGN] rendement agricole [Termes IGN] surveillance agricole Résumé : (auteur) Crop lodging - the bending of crop stems from their upright position or the failure of root-soil anchorage systems - is a major yield-reducing factor in wheat and causes deterioration of grain quality. The severity of lodging can be measured by a lodging score (LS)- an index calculated from the crop angle of inclination (CAI) and crop lodged area (LA). LS is difficult and time consuming to measure manually meaning that information on lodging occurrence and severity is limited and sparse. Remote sensing-based estimates of LS can provide more timely, synoptic and reliable information on crop lodging across vast areas. This information could improve estimates of crop yield losses, inform insurance loss adjusters and influence management decisions for subsequent seasons. This research - conducted in the 600 ha wheat sown area in the Bonifiche Ferraresi farm, located in Jolanda di Savoia, Ferrara, Italy - evaluated the performance of RADARSAT-2 and Sentinel-1 data to discriminate and classify lodging severity based on field measured LS. We measured temporal crop status characteristics related to lodging (e.g. lodged area, CAI, crop height) and collected relevant meteorological data (wind speed and rainfall) throughout May-June 2018. These field measurements were used to distinguish healthy (He) wheat from lodged wheat with different degrees of lodging severity (moderate, severe and very severe). We acquired multi-incidence angle (FQ8-27° and FQ21-41°) RADARSAT-2 and Sentinel-1 (40°) images and derived multiple metrics from them to discriminate and classify lodging severity. As a part of our data exploration, we performed a correlation analysis between the image-based metrics and LS. Next, a multi-temporal discriminant analysis approach, including a partial least squares (PLS-DA) method, was developed to classify lodging severities. We used the area under the curve-receiver operating characteristics (AUC-ROC) and confusion matrices to evaluate the accuracy of the PLS-DA classification models. Results show that (1) volume scattering components were highly correlated with LS at low incidence angles while double and surface scattering was more prevalent at high incidence angles; (2) lodging severity was best classified using low incidence angle R-FQ8 data (overall accuracy 72%) and (3) the Sentinel-1 data-based classification model was able to correctly identify 60% of the lodging severity cases in the study site. The results from this first study on classifying lodging severity using satellite-based SAR platforms suggests that SAR-based metrics can capture a substantial proportion of the observed variation in lodging severity, which is important in the context of operational crop lodging assessment in particular, and sustainable agriculture in general. Numéro de notice : A2020-276 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.04.012 Date de publication en ligne : 29/04/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.04.012 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95087 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020061	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2020063	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020062	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Integrating urban and national forest inventory data in support of rural–urban assessments / James A. Westfall in Forestry, an international journal of forest research, vol 91 n° 5 (December 2018)  

Public [article]  inForestry, an international journal of forest research > vol 91 n° 5 (December 2018) . - pp 641 - 649 Titre : Integrating urban and national forest inventory data in support of rural–urban assessments Type de document : Article/Communication Auteurs : James A. Westfall, Auteur ; Paul L. Patterson, Auteur ; Christopher B. Edgar, Auteur Année de publication : 2018 Article en page(s) : pp 641 - 649 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] agrégation [Termes IGN] Austin (Texas) [Termes IGN] intégration de données [Termes IGN] inventaire forestier étranger (données) [Termes IGN] inventaire forestier local [Termes IGN] Texas (Etats-Unis) [Termes IGN] variance [Vedettes matières IGN] Inventaire forestier Résumé : (Auteur) Due to the interest in status and trends in forest resources, many countries conduct a national forest inventory (NFI). To better understand the characteristics of woody vegetation in areas that are typically not forested, there is an increasing emphasis on urban inventory efforts where all trees both within and outside forest areas are measured. Often, these two inventories are entirely independent endeavours from data collection through analytical reporting. To holistically explore landscape-scale phenomena across the rural–urban gradient, there is a need to combine information from both sources. In this paper, methods for combining these two data sources are examined using data from an urban inventory conducted in Austin, Texas, USA, and NFI data collected in the same and surrounding areas. Approaches to aggregating areas based on sampling intensity and plot design combinations are of considerable importance for the validity of the estimation. An additional complexity can also arise due to temporal discrepancies between the two data sources. Thus, it is imperative to accurately identify all the existing sampling intensity/plot design combinations within the population of interest. Once this difficulty is surmounted, there still exist aggregation methods that will produce erroneous results. Statistically valid variance estimation arises from maintaining independence of the two samples. This approach satisfies both the proportional allocation among strata requirement as well as the necessary partitioning of the two plot designs. Difficulty in interpretation of results can also be encountered due to differences in measurement protocols across aggregated areas. Thus, analysts should have an in-depth understanding of data sources and the differences between them to avoid unintended errors. The need for rural–urban assessments are expected to increase dramatically as urban areas expand and issues such as land conversion, wildland fire and invasive species spread become of further importance. Numéro de notice : A2018-638 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1093/forestry/cpy023 Date de publication en ligne : 20/07/2018 En ligne : https://doi.org/10.1093/forestry/cpy023 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93247 [article]

Estimation cohérente de l'indice de surface foliaire en utilisant des données terrestres et aéroportées / Ronghai Hu (2018)  

Permalink

PostGIS : Introduction / Fabien Guerreiro (2015)

Permalink

3D City Models and urban information: Current issues and perspectives / Roland Billen (2014)  

Permalink

Area aggregation in map generalisation by mixed-integer programming / Jan‐Henrik Haunert in International journal of geographical information science IJGIS, vol 24 n°11-12 (december 2010)  

Permalink

Analyse exploratoire des effets de support spatial et de robustesse statistique sur la fiabilité de la mesure de la (bio)diversité / Didier Josselin in Photo interpretation, European journal of applied remote sensing, vol 45 n° 1 (mars 2009)

Permalink

Fonctions d'agrégation pour l'analyse en ligne (OLAP) de données textuelles / Guy Pujolle in Ingénierie des systèmes d'information, ISI : Revue des sciences et technologies de l'information, RSTI, vol 13 n° 6 (novembre - décembre 2008)

Permalink

Contribution d'un SIG à la sélection de sites potentiels de stockage de déchets dans le district d'Abidjan (sud Côte d'Ivoire) / K.J. Kouame in Revue internationale de géomatique, vol 18 n° 2 (juin - aout 2008)  

Permalink

Regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP) / D. Guo in International journal of geographical information science IJGIS, vol 22 n° 6-7 (june 2008)  

Permalink

Sensibilité des indices de diversité à l'agrégation / I. Mahfoud in Revue internationale de géomatique, vol 17 n° 3-4 (septembre 2007 – février 2008)  

Permalink

L'évaluation globale de la sensibilité environnementale : un outil d'amélioration des études d'impacts de projets linéaires / Nathalie Molines in Revue internationale de géomatique, vol 15 n° 2 (juin – août 2005)  

Permalink