Descripteur
Documents disponibles dans cette catégorie (30)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Unsupervised pansharpening based on self-attention mechanism / Ying Qu in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)
[article]
Titre : Unsupervised pansharpening based on self-attention mechanism Type de document : Article/Communication Auteurs : Ying Qu, Auteur ; Razieh Kaviani Baghbaderani, Auteur ; Hairong Qi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 3192 - 3208 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification non dirigée
[Termes IGN] image multibande
[Termes IGN] pansharpening (fusion d'images)
[Termes IGN] pouvoir de résolution géométrique
[Termes IGN] précision infrapixellaire
[Termes IGN] reconstruction d'image
[Termes IGN] segmentation d'imageRésumé : (auteur) Pansharpening is to fuse a multispectral image (MSI) of low-spatial-resolution (LR) but rich spectral characteristics with a panchromatic image (PAN) of high spatial resolution (HR) but poor spectral characteristics. Traditional methods usually inject the extracted high-frequency details from PAN into the upsampled MSI. Recent deep learning endeavors are mostly supervised assuming that the HR MSI is available, which is unrealistic especially for satellite images. Nonetheless, these methods could not fully exploit the rich spectral characteristics in the MSI. Due to the wide existence of mixed pixels in satellite images where each pixel tends to cover more than one constituent material, pansharpening at the subpixel level becomes essential. In this article, we propose an unsupervised pansharpening (UP) method in a deep-learning framework to address the abovementioned challenges based on the self-attention mechanism (SAM), referred to as UP-SAM. The contribution of this article is threefold. First, the SAM is proposed where the spatial varying detail extraction and injection functions are estimated according to the attention representations indicating spectral characteristics of the MSI with subpixel accuracy. Second, such attention representations are derived from mixed pixels with the proposed stacked attention network powered with a stick-breaking structure to meet the physical constraints of mixed pixel formulations. Third, the detail extraction and injection functions are spatial varying based on the attention representations, which largely improves the reconstruction accuracy. Extensive experimental results demonstrate that the proposed approach is able to reconstruct sharper MSI of different types, with more details and less spectral distortion compared with the state-of-the-art. Numéro de notice : A2021-285 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3009207 Date de publication en ligne : 23/07/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3009207 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97394
in IEEE Transactions on geoscience and remote sensing > vol 59 n° 4 (April 2021) . - pp 3192 - 3208[article]Pan-sharpening via multiscale dynamic convolutional neural network / Jianwen Hu in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)
[article]
Titre : Pan-sharpening via multiscale dynamic convolutional neural network Type de document : Article/Communication Auteurs : Jianwen Hu, Auteur ; Pei Hu, Auteur ; Xudong Kang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2231 - 2244 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] données multiéchelles
[Termes IGN] image Geoeye
[Termes IGN] image multibande
[Termes IGN] image panchromatique
[Termes IGN] image Quickbird
[Termes IGN] image Worldview
[Termes IGN] pansharpening (fusion d'images)
[Termes IGN] reconstruction d'imageRésumé : (Auteur) Pan-sharpening is an effective method to obtain high-resolution multispectral images by fusing panchromatic (PAN) images with fine spatial structure and low-resolution multispectral images with rich spectral information. In this article, a multiscale pan-sharpening method based on dynamic convolutional neural network is proposed. The filters in dynamic convolution are generated dynamically and locally by the filter generation network which is different from the standard convolution and strengthens the adaptivity of the network. The dynamic filters are adaptively changed according to the input images. The proposed multiscale dynamic convolutions extract detail feature of PAN image at different scales. Multiscale network structure is beneficial to obtain effective detail features. The weights obtained by the weight generation network are used to adjust the relationship among the detail features in each scale. The GeoEye-1, QuickBird, and WorldView-3 data are used to evaluate the performance of the proposed method. Compared with the widely used state-of-the-art pan-sharpening approaches, the experimental results demonstrate the superiority of the proposed method in terms of both objective quality indexes and visual performance. Numéro de notice : A2021-216 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3007884 Date de publication en ligne : 16/07/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3007884 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97206
in IEEE Transactions on geoscience and remote sensing > Vol 59 n° 3 (March 2021) . - pp 2231 - 2244[article]
Titre : Auxiliary tasks for the conditioning of generative adversarial networks Type de document : Thèse/HDR Auteurs : Cyprien Ruffino, Auteur ; Gilles Gasso, Directeur de thèse Editeur : Rouen [France] : Institut National des Sciences Appliquées INSA Rouen Année de publication : 2021 Importance : 136 p. Format : 21 x 30 cm Note générale : bibliographie
Pour obtenir le grade de Docteur de Normandie Université, Spécialité InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification du maximum a posteriori
[Termes IGN] classification non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection d'objet
[Termes IGN] reconstruction d'image
[Termes IGN] réseau antagoniste génératif
[Termes IGN] restauration d'imageIndex. décimale : THESE Thèses et HDR Résumé : (auteur) During the last decade, Generative Adversarial Networks (GANs) have caused a tremendous leap forward in image generation as a whole. Their ability to learn very complex, high-dimension distributions not only had a huge impact on the field of generative modeling, their influence extended to the general public at large. By being the first models able generate high-dimension photo-realistic images, GANs very quickly gained popularity as an image generation and photo manipulation technique. For example, their use as "filters" became common practice on social media, but they also allowed for the rise of Deepfakes, images that have been manipulated in order to fake the identity of a person. In this thesis, we explore the conditioning of Generative Adversarial Networks, that is influencing the generation process in order to control the content of a generated image. We focus on conditioning through auxiliary tasks, that is we explicitly implement additional objective to the generative model to complement the initial goal of learning the data distribution. First, we introduce generative modeling through several examples, and present the Generative Adversarial Networks framework. We discuss theoretical interpretations of GANs as well as its most prominent issues, notably the lack of stability during training of the model and the difficulty to generate diverse samples. We review classical techniques for conditioning GANs and propose an overview of recent approaches aiming to both solve the aforementioned issues and enhance the visual quality of the generated images. Afterwards, we focus on a specific generation task that requires conditioning : image reconstruction. In a nutshell, the problem consists in recovering an image from which we only have a handful of pixels available, usually around 0.5%. It stems from an application in geostatistics, namely the reconstruction of underground terrain from a reduced amount of expensive and difficult to obtain measurements. To do so, we propose to introduce an explicit auxiliary reconstruction task to the GAN framework which, in addition to a diversity-restoring technique, allows for the generation of high-quality images that respect the given measurements. Finally, we investigate a task of domain-transfer with generative models, specifically transferring images from the RGB color domain to the polarimetric domain. Polarimetric images bear hard constraints that directly stem from the physics of polarimetry. Leveraging on the cyclic-consistency paradigm, we extend the training of generative models with auxiliary tasks that push the generator towards enforcing the polarimetric constraints. We highlight that the approach manages to generate physically realistic polarimetric. Note de contenu : Introduction
1- Introduction to Generative Adversarial Networks
2- Image reconstruction as an auxiliary task to generative modeling
3- Domain-transfer with with auxiliary tasks for generative modeling
4- Conclusion and PerspectivesNuméro de notice : 28640 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Normandie : 2021 Organisme de stage : LITIS DOI : sans En ligne : https://tel.hal.science/tel-03517304/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99721
Titre : Context-aware image super-resolution using deep neural networks Type de document : Thèse/HDR Auteurs : Mohammad Saeed Rad, Auteur ; Jean-Philippe Thiran, Directeur de thèse Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2021 Importance : 148 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée pour l'obtention du grade de Docteur ès SciencesLangues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image à basse résolution
[Termes IGN] image à haute résolution
[Termes IGN] pouvoir de résolution spectrale
[Termes IGN] reconstruction d'image
[Termes IGN] réseau antagoniste génératif
[Termes IGN] segmentation sémantique
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Image super-resolution is a classic ill-posed computer vision and image processing problem, addressing the question of how to reconstruct a high-resolution image from its low-resolution counterpart. Current state-of-the-art methods have improved the performance of the single image super-resolution task significantly by benefiting from machine learning and AI-powered algorithms, and more specifically, with the advent of Deep Learning-based approaches. Although these advances allow a machine to learn and have better exploitation of an image and its content, recent methods are still unable to constrain the plausible solution space based on the available contextual information within an image. This limitation mostly results in poor reconstructions, even for well-known types of objects and textures easily recognizable for humans. In this thesis, we aim at proving that the categorical prior, which characterizes the semantic class of a region in an image (e.g., sky, building, plant), is crucial in super-resolution task for reaching a higher reconstruction quality. In particular, we propose several approaches to improve the perceived image quality and generalization capability of deep learning-based methods by exploiting the context and semantic meaning of images. To prove the effectiveness of this categorical information, we first propose a convolutional neural network-based framework that is able to extract and use semantic information to super-resolve a given image by using multitask learning, simultaneously for learning image super-resolution and semantic segmentation. The proposed decoder is forced to explore categorical information during training, as this setting employs only one shared deep network for both semantic segmentation and super-resolution tasks. We further investigate the possibility of using semantic information by a novel objective function to introduce additional spatial control over the training process. We propose penalizing images at different semantic levels using appropriate loss terms by benefiting from our new OBB (Object, Background, and Boundary) labels generated from segmentation labels. Then, we introduce a new test time adaptation-based technique to leverage high-resolution images with perceptually similar context to a given test image to improve the reconstruction quality. We further validate this approach's effectiveness by using a novel numerical experiment analyzing the correlation between filters learned by our network and what we define as `ideal' filters. Finally, we present a generic solution to enable adapting all our previous contributions in this thesis, as well as other recent super-resolution works trained on synthetic datasets, to real-world super-resolution problem. Real-world super-resolution refers to super-resolving images with real degradations caused by physical imaging systems, instead of low-resolution images from simulated datasets assuming a simple and uniform degradation model (i.e., bicubic downsampling). We study and develop an image-to-image translator to map the distribution of real low-resolution images to the well-understood distribution of bicubically downsampled images. This translator is used as a plug-in to integrate real inputs into any super-resolution framework trained on simulated datasets. We carry out extensive qualitative and quantitative experiments for each mentioned contribution, including user studies, to compare our proposed approaches to state-of-the-art method. Note de contenu : 1- Introduction
2- Brief image super-resolution review
3- Extracting image context by multi-task learning
4- Spatial control over image genertion process
5- Test-time adaptation based on perceptual similarity
6- Integrating into real-world SR
7- ConclusionNuméro de notice : 28652 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Sciences : EPFL, Lausanne : 2021 DOI : sans En ligne : https://infoscience.epfl.ch/record/286804?ln=fr Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99790
Titre : Geometric approximation of structured scenes from images Type de document : Thèse/HDR Auteurs : Muxingzi Li, Auteur ; Renaud Marlet, Directeur de la recherche Editeur : Nice : Université Côte d'Azur Année de publication : 2021 Importance : 122 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat résentée en vue de l’obtention du grade de docteur en Informatique de l’Université Côte d’AzurLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] approximation
[Termes IGN] chaîne de traitement
[Termes IGN] détection d'objet
[Termes IGN] extraction automatique
[Termes IGN] maillage
[Termes IGN] modélisation 3D
[Termes IGN] primitive géométrique
[Termes IGN] recalage de données localisées
[Termes IGN] reconstruction d'image
[Termes IGN] scène urbaine
[Termes IGN] segmentation d'image
[Termes IGN] semis de points
[Termes IGN] superposition de données
[Termes IGN] vectorisation
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Geometric approximation of urban objects with compact and accurate representation is a challenging problem that concerns both computer vision and computer graphics communities. Existing literature mainly focuses on reconstruction from high-quality point clouds obtained by laser scanning which are too costly for many practical scenarios. This motivates the investigation into the problem of geometric approximation from low-budget image data. Dense reconstruction from a collection of images is made possible by recent advances in multi-view stereo techniques, yet the resulting point cloud is often far from perfect for generating a compact model. In particular, our goal is to describe the captured scene with a compact and accurate representation. In this thesis, we propose two generic algorithms which address different aspects of image-based geometric approximation. First, we present an algorithm for extracting and vectorizing objects in images with polygons. Second, we present a global registration algorithm from multi-modal geometric data, typically 3D point clouds and surface meshes. Both approaches exploit detection of linear geometric primitives to approximate either 2D silhouettes with polygons consisting of line segments, or 3D point sets with a collection of planar shapes. The proposed algorithms could be used sequentially to form a pipeline for geometric approximation of an urban object from a set of image data, consisting of an overhead shot for coarse model extraction and multi-view stereo data for point cloud generation. We demonstrate the robustness and scalability of our methods for structured scenes and objects, as well as applicative potential for free-form objects. Note de contenu : 1- Introduction
2- Literature review
3- Polygonal image segmentation
4- 3D registration of multi-modal geometry
5- Application to floor modeling
6- Conclusion and perspectivesNuméro de notice : 28627 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Côte d'Azur : 2021 Organisme de stage : INRIA DOI : sans En ligne : https://tel.hal.science/tel-03388295v2/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99557 Model based signal processing techniques for nonconventional optical imaging systems / Daniele Picone (2021)PermalinkUnderwater object detection and reconstruction based on active single-pixel imaging and super-resolution convolutional neural network / Mengdi Li in Sensors, vol 21 n° 1 (January 2021)PermalinkHyperspectral band selection via optimal neighborhood reconstruction / Qi Wang in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkFusion of sparse model based on randomly erased image for SAR occluded target recognition / Zhiqiang He in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)PermalinkHyperspectral unmixing using orthogonal sparse prior-based autoencoder with hyper-laplacian loss and data-driven outlier detection / Zeyang Dou in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)PermalinkMultiscale supervised kernel dictionary learning for SAR target recognition / Lei Tao in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)PermalinkPermalinkPermalinkPermalinkPermalink