Descripteur
Documents disponibles dans cette catégorie (9301)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
Etendre la recherche sur niveau(x) vers le bas
Image matching from handcrafted to deep features: A survey / Jiayi Ma in International journal of computer vision, vol 29 n° 1 (January 2021)
![]()
[article]
Titre : Image matching from handcrafted to deep features: A survey Type de document : Article/Communication Auteurs : Jiayi Ma, Auteur ; Xingyu Jiang, Auteur ; Aoxiang Fan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 23 - 79 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement d'images
[Termes IGN] appariement de graphes
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] lissage de courbe
[Termes IGN] recalage d'imageRésumé : (auteur) As a fundamental and critical task in various visual applications, image matching can identify then correspond the same or similar structure/content from two or more images. Over the past decades, growing amount and diversity of methods have been proposed for image matching, particularly with the development of deep learning techniques over the recent years. However, it may leave several open questions about which method would be a suitable choice for specific applications with respect to different scenarios and task requirements and how to design better image matching methods with superior performance in accuracy, robustness and efficiency. This encourages us to conduct a comprehensive and systematic review and analysis for those classical and latest techniques. Following the feature-based image matching pipeline, we first introduce feature detection, description, and matching techniques from handcrafted methods to trainable ones and provide an analysis of the development of these methods in theory and practice. Secondly, we briefly introduce several typical image matching-based applications for a comprehensive understanding of the significance of image matching. In addition, we also provide a comprehensive and objective comparison of these classical and latest techniques through extensive experiments on representative datasets. Finally, we conclude with the current status of image matching technologies and deliver insightful discussions and prospects for future works. This survey can serve as a reference for (but not limited to) researchers and engineers in image matching and related fields. Numéro de notice : A2021-131 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-020-01359-2 Date de publication en ligne : 04/08/2020 En ligne : https://doi.org/https://doi.org/10.1007/s11263-020-01359-2 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96967
in International journal of computer vision > vol 29 n° 1 (January 2021) . - pp 23 - 79[article]Impact of forest disturbance on InSAR surface displacement time series / Paula M. Bürgi in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)
![]()
[article]
Titre : Impact of forest disturbance on InSAR surface displacement time series Type de document : Article/Communication Auteurs : Paula M. Bürgi, Auteur ; Rowena B. Lohman, Auteur Année de publication : 2021 Article en page(s) : pp 128 - 138 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] changement d'occupation du sol
[Termes IGN] déboisement
[Termes IGN] détection de changement
[Termes IGN] détection du signal
[Termes IGN] erreur de phase
[Termes IGN] erreur systématique
[Termes IGN] image ALOS
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-SAR
[Termes IGN] retard ionosphèrique
[Termes IGN] retard troposphérique
[Termes IGN] série temporelle
[Termes IGN] Sumatra
[Termes IGN] surveillance géologiqueRésumé : (auteur) As interferometric synthetic aperture radar (InSAR) data improve in their global coverage and temporal sampling, studies of ground deformation using InSAR are becoming feasible even in heavily vegetated regions such as the American Pacific Northwest (PNW) and Sumatra. However, ongoing forest disturbance due to logging, wildfires, or disease can introduce time-variable signals which could be misinterpreted as ground displacements. This study constrains the error introduced into InSAR time series in the presence of time-variable forest disturbance using synthetic data. For satellite platforms with randomly distributed orbital positions in time (e.g., Sentinel-1), mid-time series forest disturbance results in random error on the order of 0.2 and 10 cm/year for 1-year secular and time-variable velocities, respectively. If the orbital positions are not randomly distributed in time (e.g., ALOS-1), a biased error on the order of 10 cm/year is introduced to the inferred secular velocity. A time series using real ALOS-1 data near Eugene, OR, USA, shows agreement with the bias estimated by synthetic models. Mitigation of time-variable land cover change effects can be achieved if their timing is known, either through independent observations of surface properties (e.g., Landsat/Sentinel-2) or through the use of more computationally expensive, nonlinear inversions with additional terms for the timing of height changes. Inclusion of these additional terms reduces the potential for misinterpretation of InSAR signals associated with land surface change as ground deformation. Numéro de notice : A2021-032 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2992938 Date de publication en ligne : 18/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2992938 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96727
in IEEE Transactions on geoscience and remote sensing > vol 59 n° 1 (January 2021) . - pp 128 - 138[article]Improving GEDI footprint geolocation using a high resolution digital terrain model / Anouk Schleich (2021)
![]()
Titre : Improving GEDI footprint geolocation using a high resolution digital terrain model Type de document : Article/Communication Auteurs : Anouk Schleich, Auteur ; Maxime Soma, Auteur ; Sylvie Durrieu, Auteur ; Cédric Vega , Auteur ; Jean-Pierre Renaud
, Auteur ; Olivier Bouriaud
, Auteur
Editeur : Vienne [Autriche] : Technische Universität Wien Année de publication : 2021 Collection : Geowissenschaftliche Mitteilungen, ISSN 1811-8380 num. 104 Projets : TOSCA SLIM / Conférence : SilviLaser 2021, 17th conference on Lidar Applications for Assessing and Managing Forest Ecosystems 28/09/2021 30/09/2021 Vienne + online Autriche open access proceedings Importance : pp 179 - 181 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] fauchée
[Termes IGN] géoréférencement
[Termes IGN] Global Ecosystem Dynamics Investigation lidar
[Termes IGN] modèle numérique de terrainRésumé : (auteur) [introduction] In 2018, NASA launched the Global Ecosystem Dynamics Investigation (GEDI) mission, a high resolution lidar system installed onboard the International Space Station (ISS). It is producing high quality 3D observations of the Earth surface structure, which are highly relevant to study forest ecosystems at a global scale (Qi et al. 2019). GEDI data is composed of 25 m diameter circular footprints for which the waveform of the received energy intensity returned by the ground is recorded. Each GEDI footprint is georeferenced and its positioning accuracy (for version 1 releases) is estimated at 15-20 m in planimetry with a systematic component of 8-10 m and a noise of the order of 8 m (1). A final horizontal geolocation accuracy of 8 m is expected after further processing in the final version (Dubayah et al. 2020). Compared to most other spatial satellites the ISS is much closer to earth, causing more variations in its orientation and altitude. Therefore, geolocating data acquired by ISS sensors is more diffucult than geolocating data aquired by satellites (Dou et al. 2014). An improved geolocation of GEDI data is mandatory to evaluate their quality, by comparison with other earth observation data or field measurements, and to further facilitate their integration in ecosystem monitoring approaches. We propose a method to improve the georeferencing of GEDI footprints using a precise Digital Terrain Model (DTM). Numéro de notice : C2021-053 Affiliation des auteurs : LIF+Ext (2020- ) Thématique : FORET/IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.34726/wim.1973 Date de publication en ligne : 01/12/2021 En ligne : https://doi.org/10.34726/wim.1973 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99223 Improving traffic sign recognition results in urban areas by overcoming the impact of scale and rotation / Roholah Yazdan in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)
![]()
[article]
Titre : Improving traffic sign recognition results in urban areas by overcoming the impact of scale and rotation Type de document : Article/Communication Auteurs : Roholah Yazdan, Auteur ; Masood Varshosaz, Auteur Année de publication : 2021 Article en page(s) : pp 18 - 35 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] base de données d'images
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] corrélation à l'aide de traits caractéristiques
[Termes IGN] corrélation croisée normalisée
[Termes IGN] couple stéréoscopique
[Termes IGN] détection automatique
[Termes IGN] modèle stéréoscopique
[Termes IGN] reconnaissance d'objets
[Termes IGN] segmentation d'image
[Termes IGN] SIFT (algorithme)
[Termes IGN] signalisation routière
[Termes IGN] SURF (algorithme)
[Termes IGN] Téhéran
[Termes IGN] transformation de Hough
[Termes IGN] zone urbaineRésumé : (auteur) Automatic detection and recognition of traffic signs have many applications. However, some problems can affect the accuracy of the existing algorithms, such as changes in environmental light conditions, shadows, the presence of objects of the same colour, significant changes in scale and rotation, as well as obstacles in front of the traffic signs. To overcome these difficulties, a reference image database is usually used that includes different modes of appearing the traffic signs in the images. In order to overcome the effects of scale and rotation, in this paper a new method is presented in which only one reference image is needed for each sign to recognise the traffic sign in an image. In the proposed method, imaging is done in stereo. Using the captured image pair, a virtual image is generated which is then used to recognise the sign. As a result, the recognition is carried out with a minimum number of reference images. Experiments show that the proposed algorithm significantly improves recognition results. The traffic signs are recognised with 93.1% accuracy that enjoys a 4.9% improvement over traditional methods. Numéro de notice : A2021-010 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.10.003 Date de publication en ligne : 06/11/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.10.003 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96304
in ISPRS Journal of photogrammetry and remote sensing > vol 171 (January 2021) . - pp 18 - 35[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2021011 SL Revue Centre de documentation Revues en salle Disponible 081-2021013 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2021012 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Initialization methods of convolutional neural networks for detection of image manipulations / Ivan Castillo Camacho (2021)
![]()
Titre : Initialization methods of convolutional neural networks for detection of image manipulations Titre original : Méthodes d'initialisation des réseaux de neurones convolutifs pour la détection des manipulations d'images Type de document : Thèse/HDR Auteurs : Ivan Castillo Camacho, Auteur ; Kai Wang, Directeur de thèse Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2021 Importance : 145 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de l'Université Grenoble, spécialité : signal, image, paroles, télécomsLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] altération
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] covariance
[Termes IGN] détection d'anomalie
[Termes IGN] estompage
[Termes IGN] filtre passe-haut
[Termes IGN] flux de données
[Termes IGN] infraction
[Termes IGN] manipulation de données
[Termes IGN] qualité des données
[Termes IGN] retouche
[Termes IGN] varianceIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition. Note de contenu : 1- Introduction
2- Background knowledge and state of the art
3- Random high-pass initialization
4- Data-dependent initialization
5- Revisiting the random high-pass initialization
6- Conclusions and perspectivesNuméro de notice : 28437 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : signal, image, paroles, télécoms : Grenoble : 2021 DOI : sans En ligne : https://hal.science/tel-03346063/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98833 PermalinkPermalinkLANet: Local attention embedding to improve the semantic segmentation of remote sensing images / Lei Ding in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)
PermalinkLearning-based representations and methods for 3D shape analysis, manipulation and reconstruction / Marie-Julie Rakotosaona (2021)
PermalinkPermalinkLearning disentangled representations of satellite image time series in a weakly supervised manner / Eduardo Hugo Sanchez (2021)
PermalinkPermalinkPermalinkMask R-CNN and OBIA fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors / Emilio Guirado in Sensors, vol 21 n° 1 (January 2021)
PermalinkMise en place de nouvelles méthodes d’acquisition par lasergrammétrie en milieu difficile et couvert forestier en vue de la construction d’un parc éolien / Jean-Baptiste Myotte-Duquet (2021)
PermalinkPermalinkModel based signal processing techniques for nonconventional optical imaging systems / Daniele Picone (2021)
PermalinkModélisation de l’aire de réception d’une antenne AIS en fonction de données d’altitude et de cartes de prévision de propagation d’ondes VHF / Zackary Vanche (2021)
PermalinkModélisation et raisonnement spatial flou pour l’aide à la localisation de victimes en montagne / Mattia Bunel (2021)
PermalinkModélisation et reconstitution 3D de vestiges du Struthof en relation avec le PCR à partir d’éléments historiques / Yassine Seddik (2021)
PermalinkModelling and building of a graph database of multi-source landmarks to help emergency mountain rescuers / Véronique Gendner (2021)
PermalinkModelling landslide hazards under global changes: the case of a Pyrenean valley / Séverine Bernardie in Natural Hazards and Earth System Sciences, vol 21 n° 1 (January 2021)
PermalinkMulti-modal temporal attention models for crop mapping from satellite time series / Vivien Sainte Fare Garnot (2021)
PermalinkPermalinkPermalink