Descripteur
Termes IGN > sciences naturelles > physique > optique > optique physiologique
optique physiologiqueSynonyme(s)Optométrie |
Documents disponibles dans cette catégorie (289)
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
Titre : Learning stereo reconstruction with deep neural networks Type de document : Thèse/HDR Auteurs : Stepan Tulyakov, Auteur ; François Fleuret, Directeur de thèse ; Anton Ivanov, Directeur de thèse Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2020 Importance : 139 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée à l'Ecole Polytechnique Fédérale de Lausanne pour l’obtention du grade de Docteur ès SciencesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification semi-dirigée
[Termes IGN] contrainte géométrique
[Termes IGN] couple stéréoscopique
[Termes IGN] entropie
[Termes IGN] estimateur
[Termes IGN] étalonnage géométrique
[Termes IGN] modèle stéréoscopique
[Termes IGN] profondeur
[Termes IGN] réalité de terrain
[Termes IGN] reconstruction 3D
[Termes IGN] reconstruction d'image
[Termes IGN] vision par ordinateur
[Termes IGN] vision stéréoscopiqueRésumé : (auteur) Stereo reconstruction is a problem of recovering a 3d structure of a scene from a pair of images of the scene, acquired from different viewpoints. It has been investigated for decades and many successful methods were developed. The main drawback of these methods, is that they typically utilize a single depth cue, such as parallax, defocus blur or shading, and thus are not as robust as a human visual system that simultaneously relies on a range of monocular and binocular cues. This is mainly because it is hard to manually design a model, accounting for multiple depth cues. In this work, we address this problem by focusing on deep learning-based stereo methods that can discover a model for multiple depth cues directly from training data with ground truth depth. The complexity of deep learning-based methods, however, requires very large training sets with ground truth depth, which is often hard or costly to collect. Furthermore, even when training data is available it is often contaminated with noise, which reduces the effectiveness of supervised learning. In this work, in Chapter 3 we show that it is possible to alleviate this problem by using weakly supervised learning, that utilizes geometric constraints of the problem instead of ground truth depth. Besides the large training set requirement, deep stereo methods are not as application-friendlyas traditional methods. They have a large memory footprint and their disparity range is fixed at training time. For some applications, such as satellite stereo i magery, these are serious problems since satellite images are very large, often reaching tens of megapixels, and have a variable baseline, depending on a time difference between stereo images acquisition. In this work, in Chapter 4 we address these problems by introducing a novel network architecture with a bottleneck, capable of processing large images and utilizing more context, and an estimator that makes the network less sensitive to stereo matching ambiguities and applicable to any disparity range without re-training. Because deep learning-based methods discover depth cues directly from training data, they can be adapted to new data modalities without large modifications. In this work, in Chapter 5 we show that our method, developed for a conventional frame-based camera, can be used with a novel event-based camera, that has a higher dynamic range, smaller latency, and low power consumption. Instead of sampling intensity of all pixels with a fixed frequency, this camera asynchronously reports events of significant pixel intensity changes. To adopt our method to this new data modality, we propose a novel event sequence embedding module, that firstly aggregates information locally, across time, using a novel fully-connected layer for an irregularly sampled continuous domain, and then across discrete spatial domain. One interesting application of stereo is a reconstruction of a planet’s surface topography from satellite stereo images. In this work, in Chapter 6 we describe a geometric calibration method, as well as mosaicing and stereo reconstruction tools that we developed in the framework of the doctoral project for Color and Stereo Surface Imaging System onboard of ESA’s Trace Gas Orbiter, orbiting Mars. For the calibration, we propose a novel method, relying on starfield images because large focal lengths and complex optical distortion of the instrument forbid using standard methods. Scientific and practical results of this work are widely used by a scientific community. Note de contenu : 1- Introduction
2- Background
3- Weakly supervised learning of deep patch-matching cost
4- Applications-friendly deep stereo
5- Dense deep event-based stereo
6- Calibration of a satellite stereo system
7- ConclusionsNuméro de notice : 25795 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Sciences : Lausanne : 2020 En ligne : https://infoscience.epfl.ch/record/275342?ln=fr Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95025 Context pyramidal network for stereo matching regularized by disparity gradients / Junhua Kang in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)
[article]
Titre : Context pyramidal network for stereo matching regularized by disparity gradients Type de document : Article/Communication Auteurs : Junhua Kang, Auteur ; Lin Chen, Auteur ; Fei Deng, Auteur ; Christian Heipke, Auteur Année de publication : 2019 Article en page(s) : pp 201 - 215 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement d'images
[Termes IGN] appariement de formes
[Termes IGN] apprentissage profond
[Termes IGN] chaîne de traitement
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] gradient
[Termes IGN] vision par ordinateur
[Termes IGN] vision stéréoscopiqueRésumé : (Auteur) Also after many years of research, stereo matching remains to be a challenging task in photogrammetry and computer vision. Recent work has achieved great progress by formulating dense stereo matching as a pixel-wise learning task to be resolved with a deep convolutional neural network (CNN). However, most estimation methods, including traditional and deep learning approaches, still have difficulty to handle real-world challenging scenarios, especially those including large depth discontinuity and low texture areas.
To tackle these problems, we investigate a recently proposed end-to-end disparity learning network, DispNet (Mayer et al., 2015), and improve it to yield better results in these problematic areas. The improvements consist of three major contributions. First, we use dilated convolutions to develop a context pyramidal feature extraction module. A dilated convolution expands the receptive field of view when extracting features, and aggregates more contextual information, which allows our network to be more robust in weakly textured areas. Second, we construct the matching cost volume with patch-based correlation to handle larger disparities. We also modify the basic encoder-decoder module to regress detailed disparity images with full resolution. Third, instead of using post-processing steps to impose smoothness in the presence of depth discontinuities, we incorporate disparity gradient information as a gradient regularizer into the loss function to preserve local structure details in large depth discontinuity areas.
We evaluate our model in terms of end-point-error on several challenging stereo datasets including Scene Flow, Sintel and KITTI. Experimental results demonstrate that our model decreases the estimation error compared with DispNet on most datasets (e.g. we obtain an improvement of 46% on Sintel) and estimates better structure-preserving disparity maps. Moreover, our proposal also achieves competitive performance compared to other methods.Numéro de notice : A2019-496 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.09.012 Date de publication en ligne : 27/09/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.09.012 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93729
in ISPRS Journal of photogrammetry and remote sensing > vol 157 (November 2019) . - pp 201 - 215[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019111 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019113 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2019112 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Empirical studies on the visual perception of spatial patterns in choropleth maps / Jochen Schiewe in KN, Journal of Cartography and Geographic Information, vol 69 n° 3 (September 2019)
[article]
Titre : Empirical studies on the visual perception of spatial patterns in choropleth maps Type de document : Article/Communication Auteurs : Jochen Schiewe, Auteur Année de publication : 2019 Article en page(s) : pp 217 - 228 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de données
[Termes IGN] carte choroplèthe
[Termes IGN] couleur (rédaction cartographique)
[Termes IGN] enquête
[Termes IGN] erreur systématique
[Termes IGN] rédaction cartographique
[Termes IGN] vision
[Vedettes matières IGN] CartologieRésumé : (Auteur) An essential purpose of choropleth maps is the visual perception of spatial patterns (such as the detection of hot spots or extreme values). This requires an effective and as intuitive as possible comparison of color values between different regions. Accordingly, a number of design requirements must be considered. Due to the lack of empirical evidence regarding some elementary design aspects, an online study with 260 participants was conducted. Three closely related effects were examined: the “dark-is-more bias” (i.e., the intuitive ranking of color lightness), the “area-size bias” (i.e., the neglect of small areas, since these are less dominant in perception than larger ones) and the “data-classification effect” (i.e., attention to data classification when interpreting spatial patterns). For each hypothesis, one or more maps in connection with single or multiple choice questions were presented. Users should detect extreme values, central tendencies or homogeneities of values as well as comment on their task solving certainty. In general, the hypotheses regarding the mentioned effects could be confirmed by statistical analysis. The results are used to derive conclusions and topics for future research. In particular, further comparative empirical studies are recommended to determine the best possible map types for given applications, also considering alternatives to choropleth maps. Numéro de notice : A2019-459 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s42489-019-00026-y Date de publication en ligne : 13/08/2019 En ligne : https://doi.org/10.1007/s42489-019-00026-y Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93550
in KN, Journal of Cartography and Geographic Information > vol 69 n° 3 (September 2019) . - pp 217 - 228[article]Cartographic symbol design considerations for the space–time cube / Christopher League in Cartographic journal (the), Vol 56 n° 2 (May 2019)
[article]
Titre : Cartographic symbol design considerations for the space–time cube Type de document : Article/Communication Auteurs : Christopher League, Auteur ; Patrick Kennelly, Auteur Année de publication : 2019 Article en page(s) : pp 117 - 133 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] conception cartographique
[Termes IGN] cube espace-temps
[Termes IGN] données localisées 2D
[Termes IGN] données spatiotemporelles
[Termes IGN] figuré ponctuel
[Termes IGN] saturation de la couleur
[Termes IGN] sémiologie graphique
[Termes IGN] symbole graphique 3D
[Vedettes matières IGN] GéovisualisationRésumé : (Auteur) The cartographic representation of geographic phenomena in the space–time cube comes with special challenges and opportunities when compared with two-dimensional maps. While the added dimension allows the display of attributes that vary with time, it is difficult to display rapidly varying temporal data given the limited display height. In this study, we adapt 2D cyclic point symbols to construct 3D surfaces designed along a helical path for the space–time cube. We demonstrate how these complex 3D helical surfaces can display detailed data, including data reported daily over 100 years and data reported in four-hour intervals over a year. To create the point symbols, each value is plotted along the curve of a helix, with each turn of the helix representing one year or week, respectively. The model is modified by varying the radii from the time axis to all points using the attribute value, in these cases maximum daily temperature and four-hourly ridership, and then creating a triangulated surface from the resulting points. Using techniques common to terrain representation, we apply hue and saturation to the surface based on attribute values, and lightness based on relief shading. Multiple surfaces can be displayed in a space–time cube with a consistent time interval facing the viewer, and the surfaces or viewer perspective can be rotated to display synchronized variations. We see this method as one example of how cartographic design can refine or enhance operations in the space–time cube. Numéro de notice : A2019-239 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00087041.2018.1533291 Date de publication en ligne : 29/05/2019 En ligne : https://doi.org/10.1080/00087041.2018.1533291 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92931
in Cartographic journal (the) > Vol 56 n° 2 (May 2019) . - pp 117 - 133[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 030-2019021 RAB Revue Centre de documentation En réserve L003 Disponible Smart cartographic background symbolization for map mashups in geoportals : A proof of concept by example of landuse representation / Nadia H. Panchaud in Cartographic journal (the), Vol 56 n° 1 (February 2019)
[article]
Titre : Smart cartographic background symbolization for map mashups in geoportals : A proof of concept by example of landuse representation Type de document : Article/Communication Auteurs : Nadia H. Panchaud, Auteur ; Lorenz Hurni, Auteur Année de publication : 2019 Article en page(s) : pp 42 - 58 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes IGN] application composite
[Termes IGN] cartographie par internet
[Termes IGN] conception cartographique
[Termes IGN] géoportail
[Termes IGN] niveau de gris (image)
[Termes IGN] saturation de la couleur
[Termes IGN] sémiologie graphiqueRésumé : (Auteur) Geospatial data are now widely available to the general public thanks to geoportals and online mapping platforms. However, creating a map involves more than just combining data layers. Thus we develop cartographic functions for geoportals to support better visual hierarchy in user map mashups. This includes a couple of preparatory steps followed by a smart cartographic background symbolization derived from the original layer style. We evaluate different approaches to background symbolization: greyscale, desaturation, and smart background. The different background symbolization methods are analysed with two concrete map examples and evaluated with a survey. The smart background symbolization developed in this work improves the visual hierarchy of the map mashup by reducing the visual importance of the background layers. Numéro de notice : A2019-447 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00087041.2017.1414019 Date de publication en ligne : 16/11/2018 En ligne : https://doi.org/10.1080/00087041.2017.1414019 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92793
in Cartographic journal (the) > Vol 56 n° 1 (February 2019) . - pp 42 - 58[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 030-2019011 RAB Revue Centre de documentation En réserve L003 Disponible Estimation de profondeur à partir d'images monoculaires par apprentissage profond / Michel Moukari (2019)PermalinkFusion de sets de photos provenant de capteurs différents dans le domaine de l’archéologie / Hugo De Paulis (2019)PermalinkPrise en compte des imperfections des données en entrée des calculs d’intervisibilité en montagne / Mohssine Kaouadji (2019)PermalinkTowards visual urban scene understanding for autonomous vehicle path tracking using GPS positioning data / Citlalli Gamez Serna (2019)PermalinkVision-based localization with discriminative features from heterogeneous visual data / Nathan Piasco (2019)PermalinkCartographic redundancy in reducing change blindness in detecting extreme values in spatio-temporal maps / Paweł Cybulski in ISPRS International journal of geo-information, vol 7 n° 1 (January 2018)PermalinkPermalinkVisibility widgets for unveiling occluded data in 3D terrain visualization / Martin Röhlig in Journal of Visual Languages and Computing, vol 42 (October 2017)PermalinkColour Helmholtz stereopsis for reconstruction of dynamic scenes with arbitrary unknown reflectance / Nadejda Roubtsova in International journal of computer vision, vol 124 n° 1 (August 2017)PermalinkConstrained Palette-Space Exploration / Nicolas Mellado in ACM Transactions on Graphics, TOG, Vol 36 n° 4 (July 2017)Permalink