Descripteur
Termes IGN > sciences naturelles > physique > traitement d'image > compréhension de l'image
compréhension de l'imageVoir aussi |
Documents disponibles dans cette catégorie (32)
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
Robust detection and affine rectification of planar homogeneous texture for scene understanding / Shahzor Ahmad in International journal of computer vision, vol 126 n° 8 (August 2018)
[article]
Titre : Robust detection and affine rectification of planar homogeneous texture for scene understanding Type de document : Article/Communication Auteurs : Shahzor Ahmad, Auteur ; Loong-Fah Cheong, Auteur Année de publication : 2018 Article en page(s) : pp 822 - 854 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] compréhension de l'image
[Termes IGN] méthode robuste
[Termes IGN] scène
[Termes IGN] texture d'image
[Termes IGN] transformation affineRésumé : (Auteur) Man-made environments tend to be abundant with planar homogeneous texture, which manifests as regularly repeating scene elements along a plane. In this work, we propose to exploit such structure to facilitate high-level scene understanding. By robustly fitting a texture projection model to optimal dominant frequency estimates in image patches, we arrive at a projective-invariant method to localize such generic, semantically meaningful regions in multi-planar scenes. The recovered projective parameters also allow an affine-ambiguous rectification in real-world images marred with outliers, room clutter, and photometric severities. Comprehensive qualitative and quantitative evaluations are performed that show our method outperforms existing representative work for both rectification and detection. The potential of homogeneous texture for two scene understanding tasks is then explored. Firstly, in environments where vanishing points cannot be reliably detected, or the Manhattan assumption is not satisfied, homogeneous texture detected by the proposed approach is shown to provide alternative cues to obtain a scene geometric layout. Second, low-level feature descriptors extracted upon affine rectification of detected texture are found to be not only class-discriminative but also complementary to features without rectification, improving recognition performance on the 67-category MIT benchmark of indoor scenes. One of our configurations involving deep ConvNet features outperforms most current state-of-the-art work on this dataset, achieving a classification accuracy of 76.90%. The approach is additionally validated on a set of 31 categories (mostly outdoor man-made environments exhibiting regular, repeating structure), being a subset of the large-scale Places2 scene dataset. Numéro de notice : A2018-415 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1078-2 Date de publication en ligne : 22/03/2018 En ligne : https://doi.org/10.1007/s11263-018-1078-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90898
in International journal of computer vision > vol 126 n° 8 (August 2018) . - pp 822 - 854[article]Comparative study of visual saliency maps in the problem of classification of architectural images with Deep CNNs / Abraham Montoya Obeso (2018)
Titre : Comparative study of visual saliency maps in the problem of classification of architectural images with Deep CNNs Type de document : Article/Communication Auteurs : Abraham Montoya Obeso, Auteur ; Jenny Benois-Pineau, Auteur ; Kamel Guissous , Auteur ; Valérie Gouet-Brunet , Auteur ; Mireya S. García Vázquez, Auteur ; Alejandro A. Ramírez Acosta, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2018 Projets : 2-Pas d'info accessible - article non ouvert / Conférence : IPTA 2018, 8th International Conference on Image Processing Theory, Tools and Applications 07/11/2018 10/11/2018 Xi'an Chine Proceedings IEEE Importance : pp 1 - 6 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse comparative
[Termes IGN] Bootstrap (statistique)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] compréhension de l'image
[Termes IGN] exploration de données
[Termes IGN] recherche d'image basée sur le contenu
[Termes IGN] saillance
[Termes IGN] scène urbaineRésumé : (auteur) Incorporating Human Visual System (HVS) models into building of classifiers has become an intensively researched field in visual content mining. In the variety of models of HVS we are interested in so-called visual saliency maps. Contrarily to scan-paths they model instantaneous attention assigning the degree of interestingness/saliency for humans to each pixel in the image plane. In various tasks of visual content understanding, these maps proved to be efficient stressing contribution of the areas of interest in image plane to classifiers models. In previous works saliency layers have been introduced in Deep CNNs, showing that they allow reducing training time getting similar accuracy and loss values in optimal models. In case of large image collections efficient building of saliency maps is based on predictive models of visual attention. They are generally bottom-up and are not adapted to specific visual tasks. Unless they are built for specific content, such as "urban images"-targeted saliency maps we also compare in this paper. In present research we propose a "bootstrap" strategy of building visual saliency maps for particular tasks of visual data mining. A small collection of images relevant to the visual understanding problem is annotated with gaze fixations. Then the propagation to a large training dataset is ensured and compared with the classical GBVS model and a recent method of saliency for urban image content. The classification results within Deep CNN framework are promising compared to the purely automatic visual saliency prediction. Numéro de notice : C2018-097 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IPTA.2018.8608125 Date de publication en ligne : 14/01/2019 En ligne : https://doi.org/10.1109/IPTA.2018.8608125 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95885
Titre : Effective and annotation efficient deep learning for image understanding Type de document : Thèse/HDR Auteurs : Spyridon Gidaris, Auteur ; Nikos Komodakis, Directeur de thèse Editeur : Champs/Marne : Université Paris-Est Année de publication : 2018 Importance : 236 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l’Université Paris-Est, Domaine : Traitement du Signal et des ImagesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image numérique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] compréhension de l'image
[Termes IGN] détection d'objet
[Termes IGN] prédiction
[Termes IGN] reconnaissance d'objets
[Termes IGN] segmentation sémantiqueIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Recent development in deep learning have achieved impressive results on image understanding tasks. However, designing deep learning architectures that will effectively solve the image understanding tasks of interest is far from trivial. Even more, the success of deep learning approaches heavily relies on the availability of large-size manually labeled (by humans) data. In this context, the objective of this dissertation is to explore deep learning based approaches for core image understanding tasks that would allow to increase the effectiveness with which they are performed as well as to make their learning process more annotation efficient, i.e., less dependent on the availability of large amounts of manually labeled training data. We first focus on improving the state-of-the-art on object detection. More specifically, we attempt to boost the ability of object detection systems to recognize (even difficult) object instances by proposing a multi-region and semantic segmentation-aware ConvNet-based representation that is able to capture a diverse set of discriminative appearance factors. Also, we aim to improve the localization accuracy of object detection systems by proposing iterative detection schemes and a novel localization model for estimating the bounding box of the objects. We demonstrate that the proposed technical novelties lead to significant improvements in the object detection performance of PASCAL and MS COCO benchmarks. Regarding the pixel-wise image labeling problem, we explored a family of deep neural network architectures that perform structured prediction by learning to (iteratively) improve some initial estimates of the output labels. The goal is to identify which is the optimal architecture for implementing such deep structured prediction models. In this context, we propose to decompose the label improvement task into three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w.r.t. them. We evaluate the explored architectures on the disparity estimation task and we demonstrate that the proposed architecture achieves state-of-the-art results on the KITTI 2015 benchmark.In order to accomplish our goal for annotation efficient learning, we proposed a self-supervised learning approach that learns ConvNet-based image representations by training the ConvNet to recognize the 2d rotation that is applied to the image that it gets as input. We empirically demonstrate that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. Specifically, the image features learned from this task exhibit very good results when transferred on the visual tasks of object detection and semantic segmentation, surpassing prior unsupervised learning approaches and thus narrowing the gap with the supervised case.Finally, also in the direction of annotation efficient learning, we proposed a novel few-shot object recognition system that after training is capable to dynamically learn novel categories from only a few data (e.g., only one or five training examples) while it does not forget the categories on which it was trained on. In order to implement the proposed recognition system we introduced two technical novelties, an attention based few-shot classification weight generator, and implementing the classifier of the ConvNet based recognition model as a cosine similarity function between feature representations and classification vectors. We demonstrate that the proposed approach achieved state-of-the-art results on relevant few-shot benchmarks. Note de contenu : Introduction
1- Effective deep learning for image understanding
2- Annotation deep learning for image understandingNuméro de notice : 25835 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Domaine : Traitement du Signal et des Images : Paris-Est : 2018 nature-HAL : Thèse DOI : sans En ligne : http://www.theses.fr/2018PESC1143 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95174
Titre : Mapping society : The spatial dimensions of social cartography Type de document : Monographie Auteurs : Laura Vaughan, Auteur Editeur : Londres : University College London Année de publication : 2018 Importance : 270 p. ISBN/ISSN/EAN : 978-1-78735-305-3 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie
[Termes IGN] analyse visuelle
[Termes IGN] carte thématique
[Termes IGN] compréhension de l'image
[Termes IGN] géographie sociale
[Termes IGN] interprétation (psychologie)
[Termes IGN] population urbaine
[Termes IGN] sciences humaines et sociales
[Termes IGN] société
[Termes IGN] sociologieRésumé : (éditeur) From a rare map of yellow fever in eighteenth-century New York, to Charles Booth’s famous maps of poverty in nineteenth-century London, an Italian racial zoning map of early twentieth-century Asmara, to a map of wealth disparities in the banlieues of twenty-first-century Paris, Mapping Society traces the evolution of social cartography over the past two centuries. In this richly illustrated book, Laura Vaughan examines maps of ethnic or religious difference, poverty, and health inequalities, demonstrating how they not only serve as historical records of social enquiry, but also constitute inscriptions of social patterns that have been etched deeply on the surface of cities. The book covers themes such as the use of visual rhetoric to change public opinion, the evolution of sociology as an academic practice, changing attitudes to physical disorder, and the complexity of segregation as an urban phenomenon. While the focus is on historical maps, the narrative carries the discussion of the spatial dimensions of social cartography forward to the present day, showing how disciplines such as public health, crime science, and urban planning, chart spatial data in their current practice. Containing examples of space syntax analysis alongside full colour maps and photographs, this volume will appeal to all those interested in the long-term forces that shape how people live in cities. Note de contenu : 1. Mapping the spatial logic of society
2. Disease, health and housing
3. Charles Booth and the mapping of poverty
4. Poverty mapping after Charles Booth
5. Nationalities, race and religion
6. Crime and disorder
7. ConclusionsNuméro de notice : 25798 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Monographie En ligne : https://doabooks.org/doab?func=advancedSearch&uiLanguage=en&fromWeb=1&first=1&qu [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95201 Object-based classification of terrestrial laser scanning point clouds for landslide monitoring / Andreas Mayr in Photogrammetric record, vol 32 n° 160 (December 2017)
[article]
Titre : Object-based classification of terrestrial laser scanning point clouds for landslide monitoring Type de document : Article/Communication Auteurs : Andreas Mayr, Auteur ; Martin Rutzinger, Auteur ; Magnus Bremer, Auteur ; Sander J. Oude Elberink, Auteur ; Felix Stumpf, Auteur ; Clemens Geitner, Auteur Année de publication : 2017 Conférence : VGC 2016, 2nd virtual geoscience conference 22/09/2016 23/09/2016 Bergen Norvège Proceedings Wiley Article en page(s) : pp 377 - 397 Note générale : bibliographie Langues : Français (fre) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] apprentissage automatique
[Termes IGN] classification orientée objet
[Termes IGN] compréhension de l'image
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] effondrement de terrain
[Termes IGN] relation topologique 3D
[Termes IGN] semis de points
[Termes IGN] surveillance géologiqueRésumé : (auteur) Terrestrial laser scanning (TLS) is often used to monitor landslides and other gravitational mass movements with high levels of geometric detail and accuracy. However, unstructured TLS point clouds lack semantic information, which is required to geomorphologically interpret the measured changes. Extracting meaningful objects in a complex and dynamic environment is challenging due to the objects' fuzziness in reality, as well as the variability and ambiguity of their patterns in a morphometric feature space. This work presents a point‐cloud‐based approach for classifying multitemporal scenes of a hillslope affected by shallow landslides. The 3D point clouds are segmented into morphologically homogeneous and spatially connected parts. These segments are classified into seven target classes (scarp, eroded area, deposit, rock outcrop and different classes of vegetation) in a two‐step procedure: a supervised classification step with a machine‐learning classifier using morphometric features, followed by a correction step based on topological rules. This improves the final object extraction considerably. Numéro de notice : A2017-899 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/phor.12215 Date de publication en ligne : 13/12/2017 En ligne : https://doi.org/10.1111/phor.12215 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89522
in Photogrammetric record > vol 32 n° 160 (December 2017) . - pp 377 - 397[article]Joint classification and contour extraction of large 3D point clouds / Timo Hackel in ISPRS Journal of photogrammetry and remote sensing, vol 130 (August 2017)PermalinkMotion priors based on goals hierarchies in pedestrian tracking applications / Francisco Madrigal in Machine Vision and Applications, vol 28 n° 3-4 (May 2017)PermalinkPermalinkSemantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers / Martin Weinmann in ISPRS Journal of photogrammetry and remote sensing, vol 105 (July 2015)PermalinkDistinctive 2D and 3D features for automated large-scale scene analysis in urban areas / Martin Weinmann in Computers and graphics, vol 49 (June 2015)PermalinkTerraMobilita/iQmulus urban point cloud analysis benchmark / Bruno Vallet in Computers and graphics, vol 49 (June 2015)PermalinkAAMAS'05, fifth European workshop on adaptive agents and multi-agent systems, March 21 - 22, 2005, Paris, France / Eduardo Alonso (2005)PermalinkAnalyse et segmentation de séquences d'images en vue d'une reconnaissance de formes efficace / Santiago Venegas Martinez (2002)PermalinkContribution à la modélisation topologique par vision 2D et 3D pour la navigation d'un robot mobile sur terrain naturel / Carlos Alberto Parra Rodriguez (1999)PermalinkContribution à la mise en oeuvre d'une architecture à base de connaissances pour l'interprétation de scène 2D et 3D / Fadi Sandakly (1995)Permalink