Centre dedocumentation
scientifique

Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data / Shivangi Srivastava in International journal of geographical information science IJGIS, vol 34 n° 6 (June 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 6 (June 2020) . - pp 1117 - 1136 Titre : Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data Type de document : Article/Communication Auteurs : Shivangi Srivastava, Auteur ; John E. Vargas-Muñoz, Auteur ; Sylvain Lobry, Auteur ; Devis Tuia, Auteur Année de publication : 2020 Article en page(s) : pp 1117 - 1136 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] base de données urbaines [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] données localisées libres [Termes descripteurs IGN] Ile-de-France [Termes descripteurs IGN] image Streetview [Termes descripteurs IGN] image terrestre [Termes descripteurs IGN] information géographique [Termes descripteurs IGN] méthode heuristique [Termes descripteurs IGN] OpenStreetMap [Termes descripteurs IGN] réseau social Résumé : (auteur) We study the problem of landuse characterization at the urban-object level using deep learning algorithms. Traditionally, this task is performed by surveys or manual photo interpretation, which are expensive and difficult to update regularly. We seek to characterize usages at the single object level and to differentiate classes such as educational institutes, hospitals and religious places by visual cues contained in side-view pictures from Google Street View (GSV). These pictures provide geo-referenced information not only about the material composition of the objects but also about their actual usage, which otherwise is difficult to capture using other classical sources of data such as aerial imagery. Since the GSV database is regularly updated, this allows to consequently update the landuse maps, at lower costs than those of authoritative surveys. Because every urban-object is imaged from a number of viewpoints with street-level pictures, we propose a deep-learning based architecture that accepts arbitrary number of GSV pictures to predict the fine-grained landuse classes at the object level. These classes are taken from OpenStreetMap. A quantitative evaluation of the area of Île-de-France, France shows that our model outperforms other deep learning-based methods, making it a suitable alternative to manual landuse characterization. Numéro de notice : A2020-269 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1542698 date de publication en ligne : 18/11/2018 En ligne : https://doi.org/10.1080/13658816.2018.1542698 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95041 [article]

Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning / Benjamin Kellenberger in IEEE Transactions on geoscience and remote sensing, vol 57 n° 12 (December 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 12 (December 2019) . - pp 9524 - 9533 Titre : Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning Type de document : Article/Communication Auteurs : Benjamin Kellenberger, Auteur ; Diego Marcos, Auteur ; Sylvain Lobry, Auteur ; Devis Tuia, Auteur Année de publication : 2019 Article en page(s) : pp 9524 - 9533 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] cible mobile [Termes descripteurs IGN] classification orientée objet [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] faune locale [Termes descripteurs IGN] image captée par drone [Termes descripteurs IGN] Namibie [Termes descripteurs IGN] réalité de terrain [Termes descripteurs IGN] recensement Résumé : (auteur) We present an Active Learning (AL) strategy for reusing a deep Convolutional Neural Network (CNN)-based object detector on a new data set. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled ground truth, our goal is to train an animal detector that can be reused for repeated acquisitions, e.g., in follow-up years. Domain shifts between data sets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport (OT) to find corresponding regions between the source and the target data sets in the space of CNN activations. The CNN scores in the source data set are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target data set. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing quick retrieval of true positives in the target data set, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin. Numéro de notice : A2019-598 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2927393 date de publication en ligne : 20/08/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2927393 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94592 [article]

Correcting rural building annotations in OpenStreetMap using convolutional neural networks / John E. Vargas-Muñoz in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 147 (January 2019) . - pp 283 - 293 Titre : Correcting rural building annotations in OpenStreetMap using convolutional neural networks Type de document : Article/Communication Auteurs : John E. Vargas-Muñoz, Auteur ; Sylvain Lobry, Auteur ; Alexandre X. Falcão, Auteur ; Devis Tuia, Auteur Année de publication : 2019 Article en page(s) : pp 283 - 293 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes descripteurs IGN] bati [Termes descripteurs IGN] champ aléatoire de Markov [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] correction géométrique [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] habitat rural [Termes descripteurs IGN] mise à jour de base de données [Termes descripteurs IGN] OpenStreetMap [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] Tanzanie [Termes descripteurs IGN] Zimbabwe [Termes descripteurs IGN] zone rurale Résumé : (auteur) Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines. Numéro de notice : A2019-038 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.11.010 date de publication en ligne : 06/12/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.11.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91975 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019011	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2019013	DEP-EXM	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019012	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Land cover mapping at very high resolution with rotation equivariant CNNs : Towards small yet accurate models / Diego Marcos in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 145 - part A (November 2018) Titre : Land cover mapping at very high resolution with rotation equivariant CNNs : Towards small yet accurate models Type de document : Article/Communication Auteurs : Diego Marcos, Auteur ; Michele Volpi, Auteur ; Benjamin Kellenberger, Auteur ; Devis Tuia, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] Bade-Wurtemberg (Allemagne) [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] enrichissement sémantique [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] filtrage numérique d'image [Termes descripteurs IGN] image à ultra haute résolution [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] réseau neuronal convolutif Résumé : (Auteur) In remote sensing images, the absolute orientation of objects is arbitrary. Depending on an object’s orientation and on a sensor’s flight path, objects of the same semantic class can be observed in different orientations in the same image. Equivariance to rotation, in this context understood as responding with a rotated semantic label map when subject to a rotation of the input image, is therefore a very desirable feature, in particular for high capacity models, such as Convolutional Neural Networks (CNNs). If rotation equivariance is encoded in the network, the model is confronted with a simpler task and does not need to learn specific (and redundant) weights to address rotated versions of the same object class. In this work we propose a CNN architecture called Rotation Equivariant Vector Field Network (RotEqNet) to encode rotation equivariance in the network itself. By using rotating convolutions as building blocks and passing only the values corresponding to the maximally activating orientation throughout the network in the form of orientation encoding vector fields, RotEqNet treats rotated versions of the same object with the same filter bank and therefore achieves state-of-the-art performances even when using very small architectures trained from scratch. We test RotEqNet in two challenging sub-decimeter resolution semantic labeling problems, and show that we can perform better than a standard CNN while requiring one order of magnitude less parameters. Numéro de notice : A2018-491 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.01.021 date de publication en ligne : 19/02/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.01.021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91227 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018111	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2018113	DEP-EXM	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2018112	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images / Michele Volpi in ISPRS Journal of photogrammetry and remote sensing, vol 144 (October 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 144 (October 2018) . - pp 48 - 60 Titre : Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images Type de document : Article/Communication Auteurs : Michele Volpi, Auteur ; Devis Tuia, Auteur Année de publication : 2018 Article en page(s) : pp 48 - 60 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] champ aléatoire conditionnel [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] segmentation sémantique Résumé : (Auteur) When approaching the semantic segmentation of overhead imagery in the decimeter spatial resolution range, successful strategies usually combine powerful methods to learn the visual appearance of the semantic classes (e.g. convolutional neural networks) with strategies for spatial regularization (e.g. graphical models such as conditional random fields). In this paper, we propose a method to learn evidence in the form of semantic class likelihoods, semantic boundaries across classes and shallow-to-deep visual features, each one modeled by a multi-task convolutional neural network architecture. We combine this bottom-up information with top-down spatial regularization encoded by a conditional random field model optimizing the label space across a hierarchy of segments with constraints related to structural, spatial and data-dependent pairwise relationships between regions. Our results show that such strategy provide better regularization than a series of strong baselines reflecting state-of-the-art technologies. The proposed strategy offers a flexible and principled framework to include several sources of visual and structural information, while allowing for different degrees of spatial regularization accounting for priors about the expected output structures. Numéro de notice : A2018-392 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.06.007 date de publication en ligne : 05/07/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.06.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90826 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018101	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2018103	DEP-EXM	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2018102	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Foreword to the special issue on urban remote sensing for smarter cities / Prashanth Reddy Marpu in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol 11 n° 8 (August 2018)    

Permalink

Foreword to the theme issue on geospatial computer vision / Jan Dirk Wegner in ISPRS Journal of photogrammetry and remote sensing, vol 140 (June 2018)  

Permalink

vol 140 - June 2018 - Geospatial computer vision (Bulletin de ISPRS Journal of photogrammetry and remote sensing) / Jan Dirk Wegner  

Permalink

Foreword to the Special Issue on 'GeoVision: Computer Vision for Geospatial Applications' / Devis Tuia in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol 9 n° 7 (July 2016)  

Permalink

Multiclass feature learning for hyperspectral image classification: Sparse and hierarchical solutions / Devis Tuia in ISPRS Journal of photogrammetry and remote sensing, vol 105 (July 2015)  

Permalink

Semisupervised manifold alignment of multimodal remote sensing images / Devis Tuia in IEEE Transactions on geoscience and remote sensing, vol 52 n° 12 (December 2014)  

Permalink

Semisupervised classification of remote sensing images with active queries / Jordi Munoz-Mari in IEEE Transactions on geoscience and remote sensing, vol 50 n° 10 Tome 1 (October 2012)  

Permalink

Memory-based cluster sampling for remote sensing image classification / Michele Volpi in IEEE Transactions on geoscience and remote sensing, vol 50 n° 8 (August 2012)  

Permalink