Descripteur
Documents disponibles dans cette catégorie (561)
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
Research on map emotional semantics using deep learning approach / Daping Xi in Cartography and Geographic Information Science, Vol 50 n° 5 (June 2023)
[article]
Titre : Research on map emotional semantics using deep learning approach Type de document : Article/Communication Auteurs : Daping Xi, Auteur ; Xini Hu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 465 - 480 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage profond
[Termes IGN] émotion
[Termes IGN] réseau neuronal profondRésumé : (auteur) The main purpose of the research on map emotional semantics is to describe and express the emotional responses caused by people observing images through computer technology. Nowadays, map application scenarios tend to be diversified, and the increasing demand for emotional information of map users bring new challenges for cartography. However, the lack of evaluation of emotions in the traditional map drawing process makes it difficult for the resulting maps to reach emotional resonance with map users. The core of solving this problem is to quantify the emotional semantics of maps, it can help mapmakers to better understand map emotions and improve user satisfaction. This paper aims to perform the quantification of map emotional semantics by applying transfer learning methods and the efficient computational power of convolutional neural networks (CNN) to establish the correspondence between visual features and emotions. The main contributions of this paper are as follows: (1) a Map Sentiment Dataset containing five discrete emotion categories; (2) three different CNNs (VGG16, VGG19, and InceptionV3) are applied for map sentiment classification task and evaluated by accuracy performance; (3) six different parameter combinations to conduct experiments that would determine the best combination of learning rate and batch size; and (4) the analysis of visual variables that affect the sentiment of a map according to the chart and visualization results. The experimental results reveal that the proposed method has good accuracy performance (around 88%) and that the emotional semantics of maps have some general rules. Numéro de notice : A2023-235 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2023.2172081 Date de publication en ligne : 21/02/2023 En ligne : https://doi.org/10.1080/15230406.2023.2172081 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103594
in Cartography and Geographic Information Science > Vol 50 n° 5 (June 2023) . - pp 465 - 480[article]FORMS: Forest Multiple Source height, wood volume, and biomass maps in France at 10 to 30 m resolution based on Sentinel-1, Sentinel-2, and GEDI data with a deep learning approach / Martin Schwartz in Earth System Science Data, vol 15 n° inconnu (2023)
[article]
Titre : FORMS: Forest Multiple Source height, wood volume, and biomass maps in France at 10 to 30 m resolution based on Sentinel-1, Sentinel-2, and GEDI data with a deep learning approach Type de document : Article/Communication Auteurs : Martin Schwartz, Auteur ; Philippe Ciais, Auteur ; Aurélien de Truchis, Auteur ; Jérôme Chave, Auteur ; Catherine Ottle, Auteur ; Cédric Vega , Auteur ; Jean-Pierre Wigneron, Auteur ; et al., Auteur Année de publication : 2023 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage profond
[Termes IGN] biomasse aérienne
[Termes IGN] données allométriques
[Termes IGN] Global Ecosystem Dynamics Investigation lidar
[Termes IGN] hauteur des arbres
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] inventaire forestier national (données France)
[Termes IGN] modèle numérique de surface de la canopée
[Vedettes matières IGN] Inventaire forestierRésumé : (auteur) The contribution of forests to carbon storage and biodiversity conservation highlights the need for accurate forest height and biomass mapping and monitoring. In France, forests are managed mainly by private owners and divided into small stands, requiring 10 to 50 m spatial resolution data to be correctly separated. Further, 35 % of the French forest territory is covered by mountains and Mediterranean forests which are managed very extensively. In this work, we used a deep-learning model based on multi-stream remote sensing measurements (NASA’s GEDI LiDAR mission and ESA’s Copernicus Sentinel 1 & 2 satellites) to create a 10 m resolution canopy height map of France for 2020 (FORMS-H). In a second step, with allometric equations fitted to the French National Forest Inventory (NFI) plot data, we created a 30 m resolution above-ground biomass density (AGBD) map (Mg ha-1) of France (FORMS-B). Extensive validation was conducted. First, independent datasets from Airborne Laser Scanning (ALS) and NFI data from thousands of plots reveal a mean absolute error (MAE) of 2.94 m for FORMS-H, which outperforms existing canopy height models. Second, FORMS-B was validated using two independent forest inventory datasets from the Renecofor permanent forest plot network and from the GLORIE forest inventory with MAE of 59.6 Mg ha-1 and 19.6 Mg.ha-1 respectively, providing greater performance than other AGBD products sampled over France. These results highlight the importance of coupling remote sensing technologies with recent advances in computer science to bring material insights to climate-efficient forest management policies. Additionally, our approach is based on open-access data having global coverage and a high spatial and temporal resolution, making the maps reproducible and easily scalable. FORMS products can be accessed from https://doi.org/10.5281/zenodo.7840108 (Schwartz et al., 2023). Numéro de notice : A2023-179 Affiliation des auteurs : LIF+Ext (2020- ) Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/essd-2023-196 En ligne : https://doi.org/10.5194/essd-2023-196 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103341
in Earth System Science Data > vol 15 n° inconnu (2023)[article]Optimized position estimation in mobile multipath environments using machine learning / Nesreen I. Ziedan in Navigation : journal of the Institute of navigation, vol 70 n° 2 (Summer 2023)
[article]
Titre : Optimized position estimation in mobile multipath environments using machine learning Type de document : Article/Communication Auteurs : Nesreen I. Ziedan, Auteur Année de publication : 2023 Article en page(s) : n° 569 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement
[Termes IGN] apprentissage automatique
[Termes IGN] estimation de pose
[Termes IGN] milieu urbain
[Termes IGN] signal GNSS
[Termes IGN] trajet multipleRésumé : (auteur) The positioning accuracy of global navigation satellite system receivers is frequently degraded in urban areas due to reflected signals. A moving receiver faces additional challenges because it needs to adjust to changes in the statuses of the signals received, including line-of-sight (LOS), multipath, non-LOS, or invisible. This paper proposes two new algorithms that can be used to enhance the accuracy of a moving receiver. The first algorithm is called Optimized Position Estimation (OPE). The OPE algorithm estimates the most likely paths and identifies the one with the optimal weight. The second algorithm is called Intelligent Signal Status Estimation (ISE). The ISE algorithm utilizes a self-organizing map machine-learning algorithm to estimate the probability of a change in signal status. The algorithms are tested using global positioning system C/A signals, which have over 50 changes in their statuses. The results obtained using these algorithms reveal that the accuracy is enhanced by as much as 96.3% (i.e., a 27-fold improvement) when compared to results using a conventional navigation algorithm. Numéro de notice : A2023-200 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.33012/navi.569 Date de publication en ligne : 12/09/2022 En ligne : https://doi.org/10.33012/navi.569 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103094
in Navigation : journal of the Institute of navigation > vol 70 n° 2 (Summer 2023) . - n° 569[article]Deblurring low-light images with events / Chu Zhou in International journal of computer vision, vol 131 n° 5 (May 2023)
[article]
Titre : Deblurring low-light images with events Type de document : Article/Communication Auteurs : Chu Zhou, Auteur ; Minggui Teng, Auteur ; Jin Han, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 1284 - 1298 Note générale : bilbiographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] caméra d'événement
[Termes IGN] correction d'image
[Termes IGN] filtrage du bruit
[Termes IGN] flou
[Termes IGN] image à basse résolution
[Termes IGN] image RVBRésumé : (auteur) Modern image-based deblurring methods usually show degenerate performance in low-light conditions since the images often contain most of the poorly visible dark regions and a few saturated bright regions, making the amount of effective features that can be extracted for deblurring limited. In contrast, event cameras can trigger events with a very high dynamic range and low latency, which hardly suffer from saturation and naturally encode dense temporal information about motion. However, in low-light conditions existing event-based deblurring methods would become less robust since the events triggered in dark regions are often severely contaminated by noise, leading to inaccurate reconstruction of the corresponding intensity values. Besides, since they directly adopt the event-based double integral model to perform pixel-wise reconstruction, they can only handle low-resolution grayscale active pixel sensor images provided by the DAVIS camera, which cannot meet the requirement of daily photography. In this paper, to apply events to deblurring low-light images robustly, we propose a unified two-stage framework along with a motion-aware neural network tailored to it, reconstructing the sharp image under the guidance of high-fidelity motion clues extracted from events. Besides, we build an RGB-DAVIS hybrid camera system to demonstrate that our method has the ability to deblur high-resolution RGB images due to the natural advantages of our two-stage framework. Experimental results show our method achieves state-of-the-art performance on both synthetic and real-world images. Numéro de notice : A2023-210 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11263-023-01754-5 Date de publication en ligne : 06/02/2023 En ligne : https://doi.org/10.1007/s11263-023-01754-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103062
in International journal of computer vision > vol 131 n° 5 (May 2023) . - pp 1284 - 1298[article]Transform paper-based cadastral data into digital systems using GIS and end-to-end deep learning techniques / Joseph Mango in International journal of geographical information science IJGIS, vol 37 n° 5 (May 2023)
[article]
Titre : Transform paper-based cadastral data into digital systems using GIS and end-to-end deep learning techniques Type de document : Article/Communication Auteurs : Joseph Mango, Auteur ; Moyang Wang, Auteur ; Senlin Mu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 1099 - 1127 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cadastre
[Termes IGN] apprentissage profond
[Termes IGN] données cadastrales
[Termes IGN] numérisation du cadastre
[Termes IGN] réseau neuronal artificiel
[Termes IGN] système d'information géographiqueRésumé : (auteur) Digital systems storing cadastral data in vector format are considered effective due to their ability of offering interactive services to citizens and other land-related systems. The adoption of such systems is ubiquitous, but when adopted, they create two non-compatible systems with paper-based cadastral systems whose information needs to be digitised. This study proposes a new approach that is fast and accurate for transforming paper-based cadastral data into digital systems. The proposed method involves deep-learning techniques of the LCNN and ResNet-50 for detecting cadastral parcels and their numbers, respectively, from the cadastral plans. It also contains four functions defined to speed up transformations and compilations of the cadastral plan’s data in digital systems. The LCNN is trained and validated with 968 samples. The ResNet-50 is trained and validated with 106,000 samples. The Structural-Average-Precision (sAP10) achieved with the LCNN was 0.9057. The Precision, Recall and F1-Score achieved with the ResNet-50 were 0.9650, 0.9648 and 0.9649, respectively. These results confirmed that the new method is accurate enough for implementation, and we tested it with a huge set of data from Tanzania. Its performance from the experimented data shows that the proposed method could effectively transform paper-based cadastral data into digital systems. Numéro de notice : A2023-212 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/13658816.2023.2178002 Date de publication en ligne : 22/03/2023 En ligne : https://doi.org/10.1080/13658816.2023.2178002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103139
in International journal of geographical information science IJGIS > vol 37 n° 5 (May 2023) . - pp 1099 - 1127[article]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)PermalinkMethods for matching English language addresses / Keshav Ramani in Transactions in GIS, vol 27 n° 2 (april 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)PermalinkSALT: A multifeature ensemble learning framework for mapping urban functional zones from VGI data and VHR images / Hao Wu in Computers, Environment and Urban Systems, vol 100 (March 2023)PermalinkSiamese KPConv: 3D multiple change detection from raw point clouds using deep learning / Iris de Gelis in ISPRS Journal of photogrammetry and remote sensing, vol 197 (March 2023)PermalinkA unified attention paradigm for hyperspectral image classification / Qian Liu in IEEE Transactions on geoscience and remote sensing, vol 61 n° 3 (March 2023)PermalinkAnalysing urban growth using machine learning and open data: An artificial neural network modelled case study of five Greek cities / Pavlos Tsagkis in Sustainable Cities and Society, vol 89 (February 2023)PermalinkComparative analysis of different CNN models for building segmentation from satellite and UAV images / Batuhan Sariturk in Photogrammetric Engineering & Remote Sensing, PERS, vol 89 n° 2 (February 2023)PermalinkMulti-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services / Mingyue Xu in International journal of geographical information science IJGIS, vol 37 n° 2 (February 2023)Permalink