Descripteur
Documents disponibles dans cette catégorie (10680)
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
Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks / Sina Mohammadi in ISPRS Journal of photogrammetry and remote sensing, vol 198 (April 2023)
[article]
Titre : Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks Type de document : Article/Communication Auteurs : Sina Mohammadi, Auteur ; Mariana Belgiu, Auteur ; Alfred Stein, Auteur Année de publication : 2023 Article en page(s) : pp 272 - 283 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage dirigé
[Termes IGN] apprentissage profond
[Termes IGN] carte de la végétation
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par réseau neuronal récurrent
[Termes IGN] cultures
[Termes IGN] image Landsat-ETM+
[Termes IGN] image Landsat-OLI
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] série temporelleRésumé : (auteur) Deep learning methods have achieved promising results in crop mapping using satellite image time series. A challenge still remains on how to better learn discriminative feature representations to detect crop types when the model is applied to unseen data. To address this challenge and reveal the importance of proper supervision of deep neural networks in improving performance, we propose to supervise intermediate layers of a designed 3D Fully Convolutional Neural Network (FCN) by employing two middle supervision methods: Cross-entropy loss Middle Supervision (CE-MidS) and a novel middle supervision method, namely Supervised Contrastive loss Middle Supervision (SupCon-MidS). This method pulls together features belonging to the same class in embedding space, while pushing apart features from different classes. We demonstrate that SupCon-MidS enhances feature discrimination and clustering throughout the network, thereby improving the network performance. In addition, we employ two output supervision methods, namely F1 loss and Intersection Over Union (IOU) loss. Our experiments on identifying corn, soybean, and the class Other from Landsat image time series in the U.S. corn belt show that the best set-up of our method, namely IOU+SupCon-MidS, is able to outperform the state-of-the-art methods by
scores of 3.5% and 0.5% on average when testing its accuracy across a different year (local test) and different regions (spatial test), respectively. Further, adding SupCon-MidS to the output supervision methods improves
scores by 1.2% and 7.6% on average in local and spatial tests, respectively. We conclude that proper supervision of deep neural networks plays a significant role in improving crop mapping performance. The code and data are available at: https://github.com/Sina-Mohammadi/CropSupervision.Numéro de notice : A2023-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2023.03.007 Date de publication en ligne : 29/03/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.03.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103105
in ISPRS Journal of photogrammetry and remote sensing > vol 198 (April 2023) . - pp 272 - 283[article]Light mode and dark mode: Which one is suitable when using public-facing web maps? An experimental evaluation using eye-tracking / Lige Qiao in Transactions in GIS, vol 27 n° 2 (april 2023)
[article]
Titre : Light mode and dark mode: Which one is suitable when using public-facing web maps? An experimental evaluation using eye-tracking Type de document : Article/Communication Auteurs : Lige Qiao, Auteur ; Mingguang Wu, Auteur Année de publication : 2023 Article en page(s) : pp 516 - 540 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] cognition
[Termes IGN] Google Maps
[Termes IGN] intensité lumineuse
[Termes IGN] lecture de carte
[Termes IGN] lisibilité optique
[Termes IGN] oculométrie
[Termes IGN] rayonnement lumineux
[Termes IGN] visualisation cartographique
[Termes IGN] web mapping
[Vedettes matières IGN] CartologieRésumé : (auteur) Dark maps, which are also called dark modes or dark themes, have gained popularity, but their usability has not been experimentally evaluated. This article presents a user experiment that uses eye-tracking to assess the usability of dark and light maps. Here, two widely used web maps, Google Maps and Gaode Maps, are selected at the street and city scales. Eight map-use tasks are designed and cover four operations (identify, compare, rank, and associate) with space-alone and attributes-in-space distinctions. Four pairs of map-use tasks (light-during-the-day, dark-during-the-day, dark-at-night, and light-at-night) are examined from three aspects: effectiveness, efficiency, and cognitive load. The results provide preliminary evidence that the light-during-the-day performance is generally the best in most cases, followed by the dark-at-night performance; the dark-during-the-day performance is the worst in all cases, followed by the light-at-night performance, which suggests that aligning the map design with the environment (i.e., lighting environment) is critical for better communication. The light-during-the-day performance is the best for space-alone tasks, and the dark-at-night performance is the best for attributes-in-space tasks. Our investigation also indicates that dark maps are far less favored in practice, which suggests that users' preference for using the dark mode of public-facing web maps needs to be shaped. Since light and dark maps are associated with photopic and scotopic vision, respectively, the results indicate the need for future studies on how to leverage scotopic vision to design better dark maps. Numéro de notice : A2023-196 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.13038 Date de publication en ligne : 19/03/2023 En ligne : https://doi.org/10.1111/tgis.13038 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103081
in Transactions in GIS > vol 27 n° 2 (april 2023) . - pp 516 - 540[article]Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery / Maryam Hosseini in Computers, Environment and Urban Systems, vol 101 (April 2023)
[article]
Titre : Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery Type de document : Article/Communication Auteurs : Maryam Hosseini, Auteur ; Andres Sevtsuk, Auteur ; Fabio Miranda, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 101950 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] détection d'objet
[Termes IGN] Etats-Unis
[Termes IGN] image aérienne
[Termes IGN] navigation pédestre
[Termes IGN] segmentation sémantique
[Termes IGN] système d'information géographique
[Termes IGN] trottoir
[Termes IGN] vision par ordinateurRésumé : (auteur) While cities around the world are increasingly promoting streets and public spaces that prioritize pedestrians over vehicles, significant data gaps have made pedestrian mapping, analysis, and modeling challenging to carry out. Most cities, even in industrialized economies, still lack information about the location and connectivity of their sidewalks, making it difficult to implement research on pedestrian infrastructure and holding the technology industry back from developing accurate, location-based Apps for pedestrians, wheelchair users, street vendors, and other sidewalk users. To address this gap, we have designed and implemented an end-to-end open-source tool— Tile2Net —for extracting sidewalk, crosswalk, and footpath polygons from orthorectified aerial imagery using semantic segmentation. The segmentation model, trained on aerial imagery from Cambridge, MA, Washington DC, and New York City, offers the first open-source scene classification model for pedestrian infrastructure from sub-meter resolution aerial tiles, which can be used to generate planimetric sidewalk data in North American cities. Tile2Net also generates pedestrian networks from the resulting polygons, which can be used to prepare datasets for pedestrian routing applications. The work offers a low-cost and scalable data collection methodology for systematically generating sidewalk network datasets, where orthorectified aerial imagery is available, contributing to over-due efforts to equalize data opportunities for pedestrians, particularly in cities that lack the resources necessary to collect such data using more conventional methods. Numéro de notice : A2023-187 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.compenvurbsys.2023.101950 Date de publication en ligne : 22/02/2023 En ligne : https://doi.org/10.1016/j.compenvurbsys.2023.101950 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102961
in Computers, Environment and Urban Systems > vol 101 (April 2023) . - n° 101950[article]Methods for matching English language addresses / Keshav Ramani in Transactions in GIS, vol 27 n° 2 (april 2023)
[article]
Titre : Methods for matching English language addresses Type de document : Article/Communication Auteurs : Keshav Ramani, Auteur ; Daniel Borrajo, Auteur Année de publication : 2023 Article en page(s) : pp 347 - 363 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] anglais (langue)
[Termes IGN] appariement d'adresses
[Termes IGN] apprentissage profond
[Termes IGN] base de données d'adresses
[Termes IGN] conversion de donnéesRésumé : (auteur) Addresses occupy a niche location within the landscape of textual data, due to the positional importance carried by every word, and the geographic scope it refers to. The task of matching addresses happens every day and is present in various fields such as mail redirection, entity resolution, etc. Our work defines, and formalizes a framework to generate matching and mismatching pairs of addresses in the English language, and use it to evaluate various methods to automatically perform address matching. These methods vary widely from distance-based approaches to deep learning models. By studying the Precision, Recall, and Accuracy metrics of these approaches, we obtain an understanding of the best suited method for this setting of the address matching task. Numéro de notice : A2023-195 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.13027 Date de publication en ligne : 17/03/2023 En ligne : https://doi.org/10.1111/tgis.13027 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103080
in Transactions in GIS > vol 27 n° 2 (april 2023) . - pp 347 - 363[article]Point cloud registration for LiDAR and photogrammetric data: A critical synthesis and performance analysis on classic and deep learning algorithms / Ningli Xu in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 8 (April 2023)
[article]
Titre : Point cloud registration for LiDAR and photogrammetric data: A critical synthesis and performance analysis on classic and deep learning algorithms Type de document : Article/Communication Auteurs : Ningli Xu, Auteur ; Rongjun Qin, Auteur ; Shuang Song, Auteur Année de publication : 2023 Article en page(s) : n° 100032 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] algorithme ICP
[Termes IGN] chevauchement
[Termes IGN] données lidar
[Termes IGN] processus gaussien
[Termes IGN] recalage de données localisées
[Termes IGN] semis de points
[Termes IGN] superposition de donnéesRésumé : (auteur) Three-dimensional (3D) point cloud registration is a fundamental step for many 3D modeling and mapping applications. Existing approaches are highly disparate in the data source, scene complexity, and application, therefore the current practices in various point cloud registration tasks are still ad-hoc processes. Recent advances in computer vision and deep learning have shown promising performance in estimating rigid/similarity transformation between unregistered point clouds of complex objects and scenes. However, their performances are mostly evaluated using a limited number of datasets from a single sensor (e.g. Kinect or RealSense cameras), lacking a comprehensive overview of their applicability in photogrammetric 3D mapping scenarios. In this work, we provide a comprehensive review of the state-of-the-art (SOTA) point cloud registration methods, where we analyze and evaluate these methods using a diverse set of point cloud data from indoor to satellite sources. The quantitative analysis allows for exploring the strengths, applicability, challenges, and future trends of these methods. In contrast to existing analysis works that introduce point cloud registration as a holistic process, our experimental analysis is based on its inherent two-step process to better comprehend these approaches including feature/keypoint-based initial coarse registration and dense fine registration through cloud-to-cloud (C2C) optimization. More than ten methods, including classic hand-crafted, deep-learning-based feature correspondence, and robust C2C methods were tested. We observed that the success rate of most of the algorithms are fewer than 40% over the datasets we tested and there are still are large margin of improvement upon existing algorithms concerning 3D sparse corresopondence search, and the ability to register point clouds with complex geometry and occlusions. With the evaluated statistics on three datasets, we conclude the best-performing methods for each step and provide our recommendations, and outlook future efforts. Numéro de notice : A2023-149 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.ophoto.2023.100032 Date de publication en ligne : 16/02/2023 En ligne : https://doi.org/10.1016/j.ophoto.2023.100032 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102808
in ISPRS Open Journal of Photogrammetry and Remote Sensing > vol 8 (April 2023) . - n° 100032[article]Analyse des performances de levers LiDAR via l’iPad Pro en vue de la réalisation de plans d’intérieurs et de maquettes numériques de bâtiments / Pauline Chardon in XYZ, n° 174 (mars 2023)PermalinkAssessing the cognition of movement trajectory visualizations: interpreting speed and direction / Crystal J. Bae in Cartography and Geographic Information Science, Vol 50 n° 2 (March 2023)PermalinkChatGPT pour la géomatique, potentiel d’utilisation et limites / Emmanuel Clédat in XYZ, n° 174 (mars 2023)PermalinkDeriving map images of generalised mountain roads with generative adversarial networks / Azelle Courtial in International journal of geographical information science IJGIS, vol 37 n° 3 (March 2023)PermalinkDomain adaptation in segmenting historical maps: A weakly supervised approach through spatial co-occurrence / Sidi Wu in ISPRS Journal of photogrammetry and remote sensing, vol 197 (March 2023)PermalinkGeneration of concise 3D building model from dense meshes by extracting and completing planar primitives / Xinyi Liu in Photogrammetric record, vol 38 n° 181 (March 2023)PermalinkHow does the design of landmarks on a mobile map influence wayfinding experts’ spatial learning during a real-world navigation task? / Armand Kapaj in Cartography and Geographic Information Science, Vol 50 n° 2 (March 2023)PermalinkMapping population distribution from open address data: application to mainland Portugal / Nelson Mileu in Journal of maps, vol 18 n° 3 (March 2023)PermalinkDes mesures au sol aux images satellite : quelles données pour étudier la pollution lumineuse ? / Christophe Plotard in XYZ, n° 174 (mars 2023)PermalinkNear real-time global ionospheric total electron content modeling and nowcasting based on GNSS observations / Xulei Jin in Journal of geodesy, vol 97 n° 3 (March 2023)Permalink