Centre de documentation
scientifique

Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans / Romain Loiseau (2023)  

Public Titre : Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans Type de document : Article/Communication Auteurs : Romain Loiseau , Auteur ; Elliot Vincent, Auteur ; Mathieu Aubry, Auteur ; Loïc Landrieu , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2023 Importance : 18 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] information complexe [Termes IGN] scène 3D [Termes IGN] semis de points [Termes IGN] zone urbaine Résumé : (auteur) We propose an unsupervised method for parsing large 3D scans of real-world scenes into interpretable parts. Our goal is to provide a practical tool for analyzing 3D scenes with unique characteristics in the context of aerial surveying and mapping, without relying on application-specific user annotations. Our approach is based on a probabilistic reconstruction model that decomposes an input 3D point cloud into a small set of learned prototypical shapes. Our model provides an interpretable reconstruction of complex scenes and leads to relevant instance and semantic segmentations. To demonstrate the usefulness of our results, we introduce a novel dataset of seven diverse aerial LiDAR scans. We show that our method outperforms state-of-the-art unsupervised methods in terms of decomposition accuracy while remaining visually interpretable. Our method offers significant advantage over existing approaches, as it does not require any manual annotations, making it a practical and efficient tool for 3D scene analysis. Our code and dataset are available at https://imagine.enpc.fr/~loiseaur/learnable-earth-parser Numéro de notice : P2023-005 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : sans En ligne : https://hal.science/hal-04135416 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103347

Structured learning of geospatial data / Loïc Landrieu (2023)  

Public Titre : Structured learning of geospatial data Type de document : Thèse/HDR Auteurs : Loïc Landrieu , Auteur Editeur : Champs-sur-Marne [France] : Université Gustave Eiffel Année de publication : 2023 Importance : 179 p. Format : 21 x 30 cm Note générale : Bibliographie Habilitation à Diriger des Recherches délivrée par l'Université Gustave Eiffel, Spécialité "Sciences et Technologies de l'Information Géographique" Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme Cut Pursuit [Termes IGN] apprentissage automatique [Termes IGN] carte agricole [Termes IGN] graphe [Termes IGN] lasergrammétrie [Termes IGN] reconnaissance de formes [Termes IGN] segmentation sémantique [Termes IGN] série temporelle [Termes IGN] vision par ordinateur Résumé : (auteur) This manuscript presents an overview of my work in the field of geospatial machine learning, a rapidly growing interdisciplinary field that poses many methodological challenges and has a wide range of impactful applications. Throughout my research, I have focused on developing bespoke approaches that leverage the unique properties of geospatial data to create more efficient, precise, and parsimonious models. This manuscript is divided into four main chapters, each covering a different property of geospatial data structures that can be leveraged algorithmically. The first chapter presents a versatile mathematical framework formalizing the concept of spatial regularity with graphs. We propose an efficient algorithm that tackles a broad family of spatial problems and provides novel convergence guarantees and significant speed-ups compared to generic approaches. The second chapter introduces a deep learning method that extends the idea of exploiting graph regularity to the case of massive 3D point clouds. We simplify the task of large-scale semantic segmentation by formulating it as as a small graph labelling problem. Our compact models reach high precision at a fraction of the computational cost of other approaches. In the third chapter, we present a collection of methods designed to take advantage of the data structure inherited from 3D sensors. By considering the sensors’ structure, we develop powerful networks with state-of-the-art accuracy, latency, and robustness for various applications and data types. The last chapter dives into the real-life challenge of automated satellite time series analysis for crop mapping. Recognizing the difference between such data and standard formats used in computer vision, we propose novel and streamlined architectures that achieve unprecedented precision while remaining efficient and economical in memory and preprocessing. We also introduce the task of panoptic segmentation for satellite time series and an efficient architecture to solve this problem at scale. In summary, this manuscript argues that geospatial problems represent a challenging and impactful venue for evaluating the newest machine learning and vision methods and a fertile source of inspiration for designing novel approaches. Note de contenu : 1- Introduction 2- Exploiting graph regularity 3- Exploiting the spatial regularity of 3D data 4- Exploiting the structure of 3D sensors 5- Exploiting the structure of satellite time series 6- Perspectives 7- Curriculum vitae Numéro de notice : 24107 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : IMAGERIE Nature : HDR Note de thèse : HDR: Sciences et Technologies de l’Information Geographique : UGE : 2023 Organisme de stage : LASTIG (IGN) DOI : sans En ligne : https://hal.science/tel-04095452v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103248

A survey and benchmark of automatic surface reconstruction from point clouds / Raphaël Sulzer (2023)  

Public Titre : A survey and benchmark of automatic surface reconstruction from point clouds Type de document : Article/Communication Auteurs : Raphaël Sulzer , Auteur ; Loïc Landrieu , Auteur ; Renaud Marlet, Auteur ; Bruno Vallet , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2023 Projets : BIOM / Vallet, Bruno Importance : 24 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] benchmark spatial [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] reconstruction d'objet [Termes IGN] semis de points Résumé : (auteur) We survey and benchmark traditional and novel learning-based algorithms that address the problem of surface reconstruction from point clouds. Surface reconstruction from point clouds is particularly challenging when applied to real-world acquisitions, due to noise, outliers, non-uniform sampling and missing data. Traditionally, different handcrafted priors of the input points or the output surface have been proposed to make the problem more tractable. However, hyperparameter tuning for adjusting priors to different acquisition defects can be a tedious task. To this end, the deep learning community has recently addressed the surface reconstruction problem. In contrast to traditional approaches, deep surface reconstruction methods can learn priors directly from a training set of point clouds and corresponding true surfaces. In our survey, we detail how different handcrafted and learned priors affect the robustness of methods to defect-laden input and their capability to generate geometric and topologically accurate reconstructions. In our benchmark, we evaluate the reconstructions of several traditional and learning-based methods on the same grounds. We show that learning-based methods can generalize to unseen shape categories, but their training and test sets must share the same point cloud characteristics. We also provide the code and data to compete in our benchmark and to further stimulate the development of learning-based surface reconstruction: https://github.com/raphaelsulzer/dsr-benchmark. Numéro de notice : P2023-004 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers ArXiv Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2301.13656 Date de publication en ligne : 31/01/2023 En ligne : https://hal.science/hal-03968453 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102847

Predicting vegetation stratum occupancy from airborne LiDAR data with deep learning / Ekaterina Kalinicheva in International journal of applied Earth observation and geoinformation, vol 112 (August 2022)    

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 112 (August 2022) . - n° 102863 Titre : Predicting vegetation stratum occupancy from airborne LiDAR data with deep learning Type de document : Article/Communication Auteurs : Ekaterina Kalinicheva , Auteur ; Loïc Landrieu , Auteur ; Clément Mallet , Auteur ; Nesrine Chehata , Auteur Année de publication : 2022 Projets : TOSCA-FRISBEE / Vallet, Bruno Article en page(s) : n° 102863 Note générale : bibliographie This study has been co-funded by CNES (TOSCA FRISBEE Project, convention no200769/00) and CONFETTI Project (Nouvelle Aquitaine Region project, France). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] apprentissage semi-dirigé [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] parcelle agricole [Termes IGN] régression [Termes IGN] semis de points [Termes IGN] strate végétale Résumé : (auteur) We propose a new deep learning-based method for estimating the occupancy of vegetation strata from airborne 3D LiDAR point clouds. Our model predicts rasterized occupancy maps for three vegetation strata corresponding to lower, medium, and higher cover. Our weakly-supervised training scheme allows our network to only be supervised with vegetation occupancy values aggregated over cylindrical plots containing thousands of points. Such ground truth is easier to produce than pixel-wise or point-wise annotations. Our method outperforms handcrafted and deep learning baselines in terms of precision by up to 30%, while simultaneously providing visual and interpretable predictions. We provide an open-source implementation along with a dataset of 199 agricultural plots to train and evaluate weakly supervised occupancy regression algorithms. Numéro de notice : A2022-578 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2022.102863 Date de publication en ligne : 19/07/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102863 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99425 [article]

Documents numériques

peut être téléchargé Predicting vegetation stratum ... - pdf auteur Adobe Acrobat PDF

Preface: The 2022 edition of the XXIVth ISPRS congress / Loïc Landrieu in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-3-2022 (2022 edition) . - 5 p. Titre : Preface: The 2022 edition of the XXIVth ISPRS congress Type de document : Article/Communication Auteurs : Loïc Landrieu , Auteur ; Ewelina Rupnik , Auteur ; Sander J. Oude Elberink, Auteur ; Clément Mallet , Auteur ; Nicolas Paparoditis , Auteur Année de publication : 2022 Projets : 1-Pas de projet / Vallet, Bruno Article en page(s) : 5 p. Langues : Anglais (eng) Résumé : (auteur) [introduction] We report key elements and figures related to the proceedings of the 2022 edition of the XXIVth ISPRS Congress. Despite the uncertainty and turmoil caused by the COVID-19 pandemic, the 2022 edition of the Congress is going to take place in person in Nice (France, 6-11 June 2022) and online, with a significant expected turnout: 1,600 participants have registered including 300 online participation as of April 25. The dynamic and unpredictable global health situation makes it difficult to predict participation. Numéro de notice : A2022-339 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-3-2022-1-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-3-2022-1-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100721 [article]

Multi-modal temporal attention models for crop mapping from satellite time series / Vivien Sainte Fare Garnot in ISPRS Journal of photogrammetry and remote sensing, vol 187 (May 2022)  

Permalink

Deep surface reconstruction from point clouds with visibility information / Raphaël Sulzer (2022)  

Permalink

Learning multi-view aggregation in the wild for large-scale 3D semantic segmentation / Damien Robert (2022)  

Permalink

Learning spatio-temporal representations of satellite time series for large-scale crop mapping / Vivien Sainte Fare Garnot (2022)  

Permalink

Learning surface reconstruction from point clouds in the wild / Raphaël Sulzer (2022)  

Permalink

A model you can hear: Audio identification with playable prototypes / Romain Loiseau (2022)  

Permalink

Multi-layer modeling of dense vegetation from aerial LiDAR scans / Ekaterina Kalinicheva (2022)  

Permalink

Online segmentation of LiDAR sequences: dataset and algorithm / Romain Loiseau (2022)  

Permalink

Preface: the 2022 edition of the XXIVth ISPRS congress / Loïc Landrieu (2022)  

Permalink

Crop rotation modeling for deep learning-based parcel classification from satellite time series / Félix Quinton in Remote sensing, vol 13 n° 22 (November-2 2021)  

Permalink