Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification par réseau neuronal
classification par réseau neuronalVoir aussi |
Documents disponibles dans cette catégorie (184)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
A benchmark of named entity recognition approaches in historical documents : application to 19th century French directories / Nathalie Abadie (2022)
Titre : A benchmark of named entity recognition approaches in historical documents : application to 19th century French directories Type de document : Article/Communication Auteurs : Nathalie Abadie , Auteur ; Edwin Carlinet, Auteur ; Joseph Chazalon, Auteur ; Bertrand Duménieu , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2022 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 13237 Projets : SODUCO / Perret, Julien Conférence : DAS 2022, 5th IAPR International Workshop on Document Analysis Systems 22/05/2022 25/05/2022 La Rochelle France Proceedings Springer Importance : pp 445 - 460 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] dix-neuvième siècle
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] exploration de texte
[Termes IGN] objet géohistorique
[Termes IGN] reconnaissance de noms
[Termes IGN] traitement du langage naturelRésumé : (auteur) Named entity recognition (NER) is a necessary step in many pipelines targeting historical documents. Indeed, such natural language processing techniques identify which class each text token belongs to, e.g. “person name”, “location”, “number”. Introducing a new public dataset built from 19th century French directories, we first assess how noisy modern, off-the-shelf OCR are. Then, we compare modern CNN- and Transformer-based NER techniques which can be reasonably used in the context of historical document analysis. We measure their requirements in terms of training data, the effects of OCR noise on their performance, and show how Transformer-based NER can benefit from unsupervised pre-training and supervised fine-tuning on noisy data. Results can be reproduced using resources available at https://github.com/soduco/paper-ner-bench-das22 and https://zenodo.org/record/6394464. Numéro de notice : C2022-030 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/978-3-031-06555-2_30 En ligne : http://dx.doi.org/10.1007/978-3-031-06555-2_30 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101088 Classification of mediterranean shrub species from UAV point clouds / Juan Pedro Carbonell-Rivera in Remote sensing, vol 14 n° 1 (January-1 2022)
[article]
Titre : Classification of mediterranean shrub species from UAV point clouds Type de document : Article/Communication Auteurs : Juan Pedro Carbonell-Rivera, Auteur ; Jesus Torralba, Auteur ; Javier Estornell, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 199 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] apprentissage automatique
[Termes IGN] arbuste
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par Perceptron multicouche
[Termes IGN] Espagne
[Termes IGN] Extreme Gradient Machine
[Termes IGN] forêt méditerranéenne
[Termes IGN] image captée par drone
[Termes IGN] incendie de forêt
[Termes IGN] indice de végétation
[Termes IGN] modèle de simulation
[Termes IGN] modèle numérique de terrain
[Termes IGN] parc naturel
[Termes IGN] photogrammétrie aérienne
[Termes IGN] semis de pointsRésumé : (auteur) Modelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species’ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the use of UAV-based digital aerial photogrammetry (UAV-DAP) point clouds to classify tree and shrub species in Mediterranean forests, and this information is key for the correct generation of wildfire models. In July 2020, two test sites located in the Natural Park of Sierra Calderona (eastern Spain) were analysed, registering 1036 vegetation individuals as reference data, corresponding to 11 shrub and one tree species. Meanwhile, photogrammetric flights were carried out over the test sites, using a UAV DJI Inspire 2 equipped with a Micasense RedEdge multispectral camera. Geometrical, spectral, and neighbour-based features were obtained from the resulting point cloud generated. Using these features, points belonging to tree and shrub species were classified using several machine learning methods, i.e., Decision Trees, Extra Trees, Gradient Boosting, Random Forest, and MultiLayer Perceptron. The best results were obtained using Gradient Boosting, with a mean cross-validation accuracy of 81.7% and 91.5% for test sites 1 and 2, respectively. Once the best classifier was selected, classified points were clustered based on their geometry and tested with evaluation data, and overall accuracies of 81.9% and 96.4% were obtained for test sites 1 and 2, respectively. Results showed that the use of UAV-DAP allows the classification of Mediterranean tree and shrub species. This technique opens a wide range of possibilities, including the identification of species as a first step for further extraction of structure and fuel variables as input for wildfire behaviour models. Numéro de notice : A2022-057 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs14010199 En ligne : https://doi.org/10.3390/rs14010199 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99462
in Remote sensing > vol 14 n° 1 (January-1 2022) . - n° 199[article]Contribution to object extraction in cartography : A novel deep learning-based solution to recognise, segment and post-process the road transport network as a continuous geospatial element in high-resolution aerial orthoimagery / Calimanut-Ionut Cira (2022)
Titre : Contribution to object extraction in cartography : A novel deep learning-based solution to recognise, segment and post-process the road transport network as a continuous geospatial element in high-resolution aerial orthoimagery Type de document : Thèse/HDR Auteurs : Calimanut-Ionut Cira, Auteur Editeur : Madrid [Espagne] : Universidad politécnica de Madrid Année de publication : 2022 Importance : 227 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat en Topographie, Géodésie et cartographie, Universidad politécnica de MadridLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image orientée objet
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction du réseau routier
[Termes IGN] image aérienne
[Termes IGN] orthoimage
[Termes IGN] réseau antagoniste génératif
[Termes IGN] réseau neuronal artificiel
[Termes IGN] route
[Termes IGN] segmentation sémantiqueIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Remote sensing imagery combined with deep learning strategies is often regarded as an ideal solution for interpreting scenes and monitoring infrastructures with remarkable performance levels. Remote sensing experts have been actively using deep neural networks to solve object extraction tasks in high-resolution aerial imagery by means of supervised operations. However, the extraction operation is imperfect, due to the nature of remotely sensed images (noise, obstructions, etc.), the limitations of sensing resolution, or the occlusions often present in the scenes. The road network plays an important part in transportation and, nowadays, one of the main related challenges is keeping the existent cartographic support up to date. This task can be considered very challenging due to the complex nature of the geospatial object (continuous, with irregular geometry, and significant differences in width). We also need to take into account that secondary roads represent the largest part of the road transport network, but due to the absence of clearly defined edges, and the different spectral signatures of the materials used for pavement, monitoring, and mapping them represents a great effort for public administration, and their extraction is often omitted altogether. We believe that recent advancements in machine vision can enable a successful extraction of the road structures from high-resolution, remotely sensed imagery and a greater automation of the road mapping operation. In this PhD thesis, we leverage recent computer vision advances and propose a deep learning-based end-to-end solution, capable of efficiently extracting the surface area of roads at a large scale. The novel approach is based on a disjoint execution of three different image processing operations (recognition, semantic segmentation, and post-processing with conditional generative learning) within a common framework. We focused on improving the state-of-the-art results for each of the mentioned components, before incorporating the resulting models into the proposed solution architecture. For the recognition operation, we proposed two framework candidates based on convolutional neural networks to classify roads in openly available aerial orthoimages divided in tiles of 256×256 pixels, with a spatial resolution of 0.5 m. The frameworks are based on ensemble learning and transfer learning and combine weak classifiers to leverage the strengths of different state-of-the-art models that we heavily modified for computational efficiency. We evaluated their performance on unseen test data and compared the results with those obtained by the state-of-the-art convolutional neural networks trained for the same task, observing improvements in performance metrics of 2-3%. Secondly, we implemented hybrid semantic segmentation models (where the default backbones are replaced by neural network specialised in image segmentation) and trained them with high-resolution remote sensing imagery and their correspondent ground-truth masks. Our models achieved mean increases in performance metrics of 2.7-3.5%, when compared to the original state-of-the-art semantic segmentation architectures trained from scratch for the same task. The best-performing model was integrated on a web platform that handles the evaluation of large areas, the association of the semantic predictions with geographical coordinates, the conversion of the tiles’ format, and the generation of GeoTIFF results (compatible with geospatial databases). Thirdly, the road surface area extraction task is generally carried out via semantic segmentation over remotely sensed imagery—however, this supervised learning task can be considered very costly because it requires remote sensing images labelled at pixel level and the results are not always satisfactory (presence of discontinuities, overlooked connection points, or isolated road segments). We consider that unsupervised learning (not requiring labelled data) can be employed for post-processing the geometries of geospatial objects extracted via semantic segmentation. For this reason, we also approached the post-processing of the road surface areas obtained with the best performing segmentation model to improve the initial segmentation predictions. In this line, we proposed two post-processing operations based on conditional generative learning for deep inpainting and image-to-image translation operations and trained the networks to learn the distribution of the road network present in official cartography, using a novel dataset covering representative areas of Spain. The first proposed conditional Generative Adversarial Network (cGAN) model was trained for deep inpainting operation and obtained improvements in performance metrics of maximum 1.3%. The second cGAN model was trained for image-to-image translation, is based on a popular model heavily modified for computational efficiency (a 92.4% decrease in the number of parameters in the generator network and a 61.3% decrease in the discriminator network), and achieved a maximum increase of 11.6% in performance metrics. We also conducted a qualitative comparison to visually assess the effectiveness of the generative operations and observed great improvements with respect to the initial semantic segmentation predictions. Lastly, we proposed an end-to-end processing strategy that combines image classification, semantic segmentation, and post-processing operations to extract containing road surface area extraction from high-resolution aerial orthophotography. The training of the model components was carried out on a large-scale dataset containing more than 537,500 tiles, covering approximately 20,800 km2 of the Spanish territory, manually tagged at pixel level. The consecutive execution of the resulting deep learning models delivered higher quality results when compared to state-of-the-art implementations trained for the same task. The versatility and flexibility of the solution given by the disjointed execution of the three separate sub-operations proved its effectiveness and economic efficiency and enables the integration of a web application that alleviates the manipulation of geospatial data, while allowing for an easy integration of future models and algorithms. Resuming, applying the proposed models resulted from this PhD thesis translates to operations aimed to check if the latest existing aerial orthoimages contains the studied continuous geospatial element, to obtain an approximation of its surface area using supervised learning and to improve the initial segmentation results with post-processing methods based on conditional generative learning. The results obtained with the proposed end-to-end-solution presented in this PhD thesis improve the state-of-the-art in the field of road extraction with deep learning techniques and prove the appropriateness of applying the proposed extraction workflow for a more robust and more efficient extraction operation of the road transport network. We strongly believe that the processing strategy can be applied to enhance other similar extraction tasks of continuous geospatial elements (such as the mapping of riverbeds, or railroads), or serve as a base for developing additional extraction workflows of geospatial objects from remote sensing images. Note de contenu : 1- Introduction
2- Methodology
3- Theoretical framework
4- Litterature review
5- Road recognition: A framework based on nestion of convolutional neuronal networks and transfer learning to regognise road elements
6- Road segmentation: An approach based on hybrid semantic segmentation models to extract the surface area of rod elements from aerial orthoimagery
7- Post-processing of semantic segmentation predictions I: A conditional generative adversial network to improve the extraction of road surface areas via deep inpainting operations
8- Post-processing of semantic segmentation predictions II: A lightweight conditional generative adversial network to improve the extraction of road surface areas via image-to-image translation
9- An end-to-end road extraction solution based on regonition, segmentation, and post-processing operations for a large-scale mapping of the road transport network from aerial orthophotography
10- ConclusionsNuméro de notice : 24069 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Topographie, Géodésie et cartographie : Universidad politécnica de Madrid : 2022 DOI : 10.20868/UPM.thesis.70152 En ligne : https://doi.org/10.20868/UPM.thesis.70152 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102113 Conventional and neural network-based water vapor density model for GNSS troposphere tomography / Chen Liu in GPS solutions, vol 26 n° 1 (January 2022)
[article]
Titre : Conventional and neural network-based water vapor density model for GNSS troposphere tomography Type de document : Article/Communication Auteurs : Chen Liu, Auteur ; Yibin Yao, Auteur ; Chaoqian Xu, Auteur Année de publication : 2022 Article en page(s) : n° 4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] classification par réseau neuronal
[Termes IGN] erreur absolue
[Termes IGN] étalonnage de modèle
[Termes IGN] modèle météorologique
[Termes IGN] propagation troposphérique
[Termes IGN] tomographie par GPS
[Termes IGN] vapeur d'eau
[Termes IGN] voxelRésumé : (auteur) Global navigation satellite system (GNSS) water vapor (WV) tomography is a promising technique to reconstruct the three-dimensional (3D) WV field. However, this technique usually suffers from the ill-posed problem caused by the poor geometry of GNSS rays, resulting in underdetermined tomographic equations. Such equations often rely on iterative methods for solving, but conventional iterative approaches require accurate initial WV density. To address this demand, we proposed two models for WV density estimation. One is the conventional model (CO model) that consists of an exponential model and a linear least-squares model, which are used to describe the spatial and temporal variability of the WV density, respectively. The other is a neural network model (NN model) that uses a backpropagation neural network (BPNN) to fit the nonlinear variation of WV density in both spatial and temporal domains. WV density derived from a Hong Kong (HK) radiosonde station (RS) during 2020 was used to validate the proposed models. Validation results show that both models well describe the spatial and temporal distribution of the WV density. The NN model exhibits better prediction performance than the CO model in terms of root mean square error (RMSE) and bias. We also applied the proposed models to GNSS WV tomography to test their performance in extreme weather conditions. Test results show that the proposed model-based GNSS tomography can correct the content of WV density but cannot accurately sense its irregular distribution. Numéro de notice : A2022-005 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10291-021-01188-x Date de publication en ligne : 23/10/2021 En ligne : https://doi.org/10.1007/s10291-021-01188-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98920
in GPS solutions > vol 26 n° 1 (January 2022) . - n° 4[article]Deep image translation with an affinity-based change prior for unsupervised multimodal change detection / Luigi Tommaso Luppino in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)
[article]
Titre : Deep image translation with an affinity-based change prior for unsupervised multimodal change detection Type de document : Article/Communication Auteurs : Luigi Tommaso Luppino, Auteur ; Michael Kampffmeyer, Auteur ; filipo Maria Bianchi, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4700422 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] analyse comparative
[Termes IGN] architecture de réseau
[Termes IGN] classification non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de changement
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] réseau antagoniste génératifRésumé : (auteur) Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology. Numéro de notice : A2022-027 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2021.3056196 Date de publication en ligne : 17/02/2021 En ligne : https://doi.org/10.1109/TGRS.2021.3056196 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99263
in IEEE Transactions on geoscience and remote sensing > vol 60 n° 1 (January 2022) . - n° 4700422[article]PermalinkPermalinkPermalinkDetection of windthrown tree stems on UAV-orthomosaics using U-Net convolutional networks / Stefan Reder in Remote sensing, vol 14 n° 1 (January-1 2022)PermalinkEffective 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)PermalinkÉléments pour l'analyse et le traitement d'images : application à l'estimation de la qualité du bois / Rémy Decelle (2022)PermalinkExploring data fusion for multi-object detection for intelligent transportation systems using deep learning / Amira Mimouna (2022)PermalinkGénération d’un jeu de données d’entraînement et mise en oeuvre d’une architecture de détection par deep learning des numéros de parcelles sur les plans du cadastre Napoléonien / Tiecoumba Ibrahim Tamela (2022)PermalinkA GIS-based landslide susceptibility mapping and variable importance analysis using artificial intelligent training-based methods / Pengxiang Zhao in Remote sensing, vol 14 n° 1 (January-1 2022)PermalinkGlobal canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles / Nico Lang in Remote sensing of environment, vol 268 (January 2022)Permalink