Centre dedocumentation
scientifique

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)  

Public [article]  inEarth System Science Data > vol 15 n° inconnu (2023) 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 forestier Résumé : (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 [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)  

Public [article]  inNavigation : journal of the Institute of navigation > vol 70 n° 2 (Summer 2023) . - n° 569 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 multiple Résumé : (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 [article]

Deblurring low-light images with events / Chu Zhou in International journal of computer vision, vol 131 n° 5 (May 2023)  

Public [article]  inInternational journal of computer vision > vol 131 n° 5 (May 2023) . - pp 1284 - 1298 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 RVB Résumé : (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 [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)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 37 n° 5 (May 2023) . - pp 1099 - 1127 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 géographique Résumé : (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 [article]

Automatic generation of outline-based representations of landmark buildings with distinctive shapes / Peng Ti in International journal of geographical information science IJGIS, vol 37 n° 4 (April 2023)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 37 n° 4 (April 2023) . - pp 864 - 884 Titre : Automatic generation of outline-based representations of landmark buildings with distinctive shapes Type de document : Article/Communication Auteurs : Peng Ti, Auteur ; Tao Xiong, Auteur ; Yuhong Qiu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 864 - 884 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Bâti-3D [Termes IGN] cartographie [Termes IGN] contour [Termes IGN] détection du bâti [Termes IGN] extraction de traits caractéristiques [Termes IGN] raisonnement spatial [Termes IGN] reconnaissance de formes [Termes IGN] segmentation d'image [Termes IGN] sémiologie graphique [Vedettes matières IGN] Géovisualisation Résumé : (auteur) Landmark buildings are salient features for spatial cognition on maps. Distinctive outlines are the major visual characteristics that separate landmark buildings from their surrounding environments. The automatic symbolization of landmark outlines facilitates recognition and map production. As users often recognize landmarks by the outlines of their façades from a street view, this study proposes an automatic method for automatically generating representations of the outlines of landmark buildings in four steps: (1) extract outlines from street-view photographs using GrabCut method, (2) vectorize the extracted building outlines, (3) simplify outline shapes, and (4) symbolize the simplified building outlines in three dimensions (3D). We used the proposed method to generate test data with symbolized outlines for eight buildings in a real-world environment for a wayfinding experiment in which the subjects used the building representations to identify landmark buildings and evaluated their perception of the generated maps. The subjects successfully recognized these buildings based on the symbolized outlines on a map, expressed satisfaction with the manually generated 3D symbols, and reported the same or similar ease of building recognition using 2D or 3D symbolized outlines. Numéro de notice : A2023-207 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2143503 Date de publication en ligne : 11/11/2022 En ligne : https://doi.org/10.1080/13658816.2022.2143503 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103109 [article]

Evaluating future railway-induced urban growth of twelve cities using multiple SLEUTH models with open-source geospatial inputs / Alvin Christopher G. Varquez in Sustainable Cities and Society, vol 91 (April 2023)  

Permalink

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)  

Permalink

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)  

Permalink

Methods for matching English language addresses / Keshav Ramani in Transactions in GIS, vol 27 n° 2 (april 2023)  

Permalink

ChatGPT pour la géomatique, potentiel d’utilisation et limites / Emmanuel Clédat in XYZ, n° 174 (mars 2023)

Permalink

Deriving 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)  

Permalink

Domain 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)  

Permalink

How 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)  

Permalink

Residents’ Experiential Knowledge and Its Importance for Decision-Making Processes in Spatial Planning: A PPGIS Based Study / Edyta Bąkowska-Waldmann in ISPRS International journal of geo-information, vol 12 n° 3 (March 2023)  

Permalink

SALT: 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)  

Permalink