Centre de documentation
scientifique

Leveraging deep learning and remote sensing to predict ecosystem types in the NiN framework / Matteo Crespin-Jouan (2024)

Public Titre : Leveraging deep learning and remote sensing to predict ecosystem types in the NiN framework Type de document : Mémoire Auteurs : Matteo Crespin-Jouan, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2024 Importance : 41 p. Format : 21 x 30 cm Note générale : bibliographie Mémoire d'ingénieur 2e année Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage profond [Termes IGN] cartographie [Termes IGN] couverture (données géographiques) [Termes IGN] gradient [Termes IGN] occupation du sol [Termes IGN] Sentinel-2 [Termes IGN] télédétection [Termes IGN] végétation Index. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (auteur) Ce rapport présente les résultats d’un stage effectué au sein du Geo-Ecology Research Group (GEco) du Muséum d’Histoire Naturelle d’Oslo. Le projet a porté sur l’application de techniques d’apprentissage profond pour classifier les écosystèmes norvégiens en se basant sur les données du système de classification Natur i Norge (NiN). Différentes sources de données ont été utilisées notamment des images aériennes de drones, des photos prises au sol et des données satellitaires Sentinel, afin de prédire les types d’écosystèmes et des gradients environnementaux clés, tels que la richesse en calcaire. L’étude a exploré différentes approches, notamment les réseaux neuronaux convolutifs (CNN) et les perceptrons multicouches (MLP), en mettant l’accent sur l’exploitation des informations spectrales plutôt que des caractéristiques spatiales. Les résultats ont mis en évidence les défis liés au travail avec des données limitées et incohérentes, en particulier dans le contexte de classifications très détaillée comme NiN. Bien que les modèles aient montré un certain succès, notamment avec l’utilisation de données hyperspectrales, les résultats ont été limités par la qualité et la cohérence des labels disponibles. Note de contenu : Introduction 1. About the Data, the labels, and the distribution of the labels in the datasets 2. CNNs and vision transformers to leverage shape and texture features 3. A more successful endeavour : a mere mutliplayer perceptron on hyper-spectral satellite images Conclusion Numéro de notice : 24266 Affiliation des auteurs : IGN (2020- ) Thématique : BIODIVERSITE/GEOMATIQUE/INFORMATIQUE Nature : Mémoire de projet pluridisciplinaire Organisme de stage : Geo-Ecology Research Group (GEco), at Oslo’s Natural History Museum (NHM) Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103901

Assuring the quality of VGI on land use and land cover: experiences and learnings from the LandSense project / Giles M. Foody in Geo-spatial Information Science, vol 26 n° inconnu ([01/08/2023])  

Public [article]  inGeo-spatial Information Science > vol 26 n° inconnu [01/08/2023] . - n° 2100285 Titre : Assuring the quality of VGI on land use and land cover: experiences and learnings from the LandSense project Type de document : Article/Communication Auteurs : Giles M. Foody, Auteur ; Gavin Long, Auteur ; Michael Schultz, Auteur ; Ana-Maria Olteanu-Raimond , Auteur Année de publication : 2023 Projets : Landsense / Raimond, Ana-Maria Article en page(s) : n° 2100285 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes IGN] assurance qualité [Termes IGN] données localisées des bénévoles [Termes IGN] occupation du sol [Termes IGN] qualité des données [Termes IGN] utilisation du sol Résumé : (auteur) The potential of citizens as a source of geographical information has been recognized for many years. Such activity has grown recently due to the proliferation of inexpensive location aware devices and an ability to share data over the internet. Recently, a series of major projects, often cast as citizen observatories, have helped explore and develop this potential for a wide range of applications. Here, some of the experiences and learnings gained from part of one such project, which aimed to further the role of citizen science within Earth observation and help address environmental challenges, LandSense, are shared. The key focus is on quality assurance of citizen generated data on land use and land cover especially to support analyses of remotely sensed data and products. Particular focus is directed to quality assurance checks on photographic image quality, privacy, polygon overlap, positional accuracy and offset, contributor agreement, and categorical accuracy. The discussion aims to provide good practice advice to aid future studies and help fulfil the full potential of citizens as a source of volunteered geographical information (VGI). Numéro de notice : A2023-081 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10095020.2022.2100285 Date de publication en ligne : 21/07/2022 En ligne : https://doi.org/10.1080/10095020.2022.2100285 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101337 [article]

Towards global scale segmentation with OpenStreetMap and remote sensing / Munazza Usmani in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 8 (April 2023)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 8 (April 2023) . - n° 100031 Titre : Towards global scale segmentation with OpenStreetMap and remote sensing Type de document : Article/Communication Auteurs : Munazza Usmani, Auteur ; Maurizio Napolitano, Auteur ; Francesca Bovolo, Auteur Année de publication : 2023 Article en page(s) : n° 100031 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] bâtiment [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données localisées des bénévoles [Termes IGN] image à haute résolution [Termes IGN] information sémantique [Termes IGN] occupation du sol [Termes IGN] OpenStreetMap [Termes IGN] segmentation d'image [Termes IGN] segmentation sémantique [Termes IGN] utilisation du sol Résumé : (auteur) Land Use Land Cover (LULC) segmentation is a famous application of remote sensing in an urban environment. Up-to-date and complete data are of major importance in this field. Although with some success, pixel-based segmentation remains challenging because of class variability. Due to the increasing popularity of crowd-sourcing projects, like OpenStreetMap, the need for user-generated content has also increased, providing a new prospect for LULC segmentation. We propose a deep-learning approach to segment objects in high-resolution imagery by using semantic crowdsource information. Due to satellite imagery and crowdsource database complexity, deep learning frameworks perform a significant role. This integration reduces computation and labor costs. Our methods are based on a fully convolutional neural network (CNN) that has been adapted for multi-source data processing. We discuss the use of data augmentation techniques and improvements to the training pipeline. We applied semantic (U-Net) and instance segmentation (Mask R-CNN) methods and, Mask R–CNN showed a significantly higher segmentation accuracy from both qualitative and quantitative viewpoints. The conducted methods reach 91% and 96% overall accuracy in building segmentation and 90% in road segmentation, demonstrating OSM and remote sensing complementarity and potential for city sensing applications. Numéro de notice : A2023-148 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.ophoto.2023.100031 Date de publication en ligne : 16/02/2023 En ligne : https://doi.org/10.1016/j.ophoto.2023.100031 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102807 [article]

Generation 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)  

Public [article]  inPhotogrammetric record > vol 38 n° 181 (March 2023) . - pp 22 - 46 Titre : Generation of concise 3D building model from dense meshes by extracting and completing planar primitives Type de document : Article/Communication Auteurs : Xinyi Liu, Auteur ; Xianzhang Zhu, Auteur ; Yongjun Zhang, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 22 - 46 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie [Termes IGN] adjacence [Termes IGN] bati [Termes IGN] maillage [Termes IGN] modélisation 3D du bâti BIM [Termes IGN] modélisation du bâti [Termes IGN] primitive géométrique [Termes IGN] reconstruction 3D [Termes IGN] segmentation en plan [Termes IGN] semis de points Résumé : (auteur) The generation of a concise building model has been and continues to be a challenge in photogrammetry and computer graphics. The current methods typically focus on the simplicity and fidelity of the model, but those methods either fail to preserve the structural information or suffer from low computational efficiency. In this paper, we propose a novel method to generate concise building models from dense meshes by extracting and completing the planar primitives of the building. From the perspective of probability, we first extract planar primitives from the input mesh and obtain the adjacency relationships between the primitives. Since primitive loss and structural defects are inevitable in practice, we employ a novel structural completion approach to eliminate linkage errors. Finally, the concise polygonal mesh is reconstructed by connectivity-based primitive assembling. Our method is efficient and robust to various challenging data. Experiments on various building models revealed the efficacy and applicability of our method. Numéro de notice : A2023-162 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/phor.12438 Date de publication en ligne : 04/01/2023 En ligne : https://doi.org/10.1111/phor.12438 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102865 [article]

Siamese 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)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 197 (March 2023) . - pp 274 - 291 Titre : Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning Type de document : Article/Communication Auteurs : Iris de Gelis, Auteur ; Sébastien Lefèvre, Auteur ; Thomas Corpetti, Auteur Année de publication : 2023 Article en page(s) : pp 274 - 291 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] apprentissage profond [Termes IGN] bâtiment [Termes IGN] détection de changement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] modèle numérique de surface [Termes IGN] réseau neuronal siamois [Termes IGN] semis de points [Termes IGN] végétation [Termes IGN] zone urbaine Résumé : (auteur) This study is concerned with urban change detection and categorization in point clouds. In such situations, objects are mainly characterized by their vertical axis, and the use of native 3D data such as 3D Point Clouds (PCs) is, in general, preferred to rasterized versions because of significant loss of information implied by any rasterization process. Yet, for obvious practical reasons, most existing studies only focus on 2D images for change detection purpose. In this paper, we propose a method capable of performing change detection directly within 3D data. Despite recent deep learning developments in remote sensing, to the best of our knowledge there is no such method to tackle multi-class change segmentation that directly processes raw 3D PCs. Thereby, based on advances in deep learning for change detection in 2D images and for analysis of 3D point clouds, we propose a deep Siamese KPConv network that deals with raw 3D PCs to perform change detection and categorization in a single step. Experimental results are conducted on synthetic and real data of various kinds (LiDAR, multi-sensors). Tests performed on simulated low density LiDAR and multi-sensor datasets show that our proposed method can obtain up to 80% of mean of IoU over classes of changes, leading to an improvement ranging from 10% to 30% over the state-of-the-art. A similar range of improvements is attainable on real data. Then, we show that pre-training Siamese KPConv on simulated PCs allows us to greatly reduce (more than 3,000 ) the annotations required on real data. This is a highly significant result to deal with practical scenarios. Finally, an adaptation of Siamese KPConv is realized to deal with change classification at PC scale. Our network overtakes the current state-of-the-art deep learning method by 23% and 15% of mean of IoU when assessed on synthetic and public Change3D datasets, respectively. The code is available at the following link: https://github.com/IdeGelis/torch-points3d-SiameseKPConv. Numéro de notice : A2023-147 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2023.02.001 Date de publication en ligne : 17/02/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.02.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102805 [article]

Comparative 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)  

Permalink

Geospatial-based machine learning techniques for land use and land cover mapping using a high-resolution unmanned aerial vehicle image / Taposh Mollick in Remote Sensing Applications: Society and Environment, RSASE, vol 29 (January 2023)  

Permalink

Landscape metrics regularly outperform other traditionally-used ancillary datasets in dasymetric mapping of population / Heng Wan in Computers, Environment and Urban Systems, vol 99 (January 2023)  

Permalink

The cellular automata approach in dynamic modelling of land use change detection and future simulations based on remote sensing data in Lahore Pakistan / Muhammad Nasar Ahmad in Photogrammetric Engineering & Remote Sensing, PERS, vol 89 n° 1 (January 2023)  

Permalink

Using Google Earth Engine to classify unique forest and agroforest classes using a mix of Sentinel 2a spectral data and topographical features: a Sri Lanka case study / W.D.K.V. Nandasena in Geocarto international, vol 38 n° inconnu ([01/01/2023])  

Permalink

Hyperspectral imagery and urban areas: results of the HYEP project / Christiane Weber in Revue Française de Photogrammétrie et de Télédétection, n° 224 (2022)  

Permalink

Integration of geospatial technologies with multiple regression model for urban land use land cover change analysis and its impact on land surface temperature in Jimma City, southwestern Ethiopia / Mitiku Badasa Moisa in Applied geomatics, vol 14 n° 4 (December 2022)  

Permalink

Mapping impervious surfaces with a hierarchical spectral mixture analysis incorporating endmember spatial distribution / Zhenfeng Shao in Geo-spatial Information Science, vol 25 n° 4 (December 2022)  

Permalink

Spatio-temporal patterns of wildfires in Siberia during 2001–2020 / Oleg Tomshin in Geocarto international, vol 37 n° 25 ([01/12/2022])  

Permalink

Urban wetland fragmentation and ecosystem service assessment using integrated machine learning algorithm and spatial landscape analysis / Das Subhasis in Geocarto international, vol 37 n° 25 ([01/12/2022])  

Permalink