Descripteur
Documents disponibles dans cette catégorie (86)
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
Deep-learning-based multispectral image reconstruction from single natural color RGB image - Enhancing UAV-based phenotyping / Jiangsan Zhao in Remote sensing, vol 14 n° 5 (March-1 2022)
[article]
Titre : Deep-learning-based multispectral image reconstruction from single natural color RGB image - Enhancing UAV-based phenotyping Type de document : Article/Communication Auteurs : Jiangsan Zhao, Auteur ; Ajay Kumar, Auteur ; Balaji Naik Banoth, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 1272; Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] agriculture de précision
[Termes IGN] apprentissage profond
[Termes IGN] erreur absolue
[Termes IGN] image multibande
[Termes IGN] image RVB
[Termes IGN] Inde
[Termes IGN] phénologie
[Termes IGN] reconstruction d'imageRésumé : (auteur) Multispectral images (MSIs) are valuable for precision agriculture due to the extra spectral information acquired compared to natural color RGB (ncRGB) images. In this paper, we thus aim to generate high spatial MSIs through a robust, deep-learning-based reconstruction method using ncRGB images. Using the data from the agronomic research trial for maize and breeding research trial for rice, we first reproduced ncRGB images from MSIs through a rendering model, Model-True to natural color image (Model-TN), which was built using a benchmark hyperspectral image dataset. Subsequently, an MSI reconstruction model, Model-Natural color to Multispectral image (Model-NM), was trained based on prepared ncRGB (ncRGB-Con) images and MSI pairs, ensuring the model can use widely available ncRGB images as input. The integrated loss function of mean relative absolute error (MRAEloss) and spectral information divergence (SIDloss) were most effective during the building of both models, while models using the MRAEloss function were more robust towards variability between growing seasons and species. The reliability of the reconstructed MSIs was demonstrated by high coefficients of determination compared to ground truth values, using the Normalized Difference Vegetation Index (NDVI) as an example. The advantages of using “reconstructed” NDVI over Triangular Greenness Index (TGI), as calculated directly from RGB images, were illustrated by their higher capabilities in differentiating three levels of irrigation treatments on maize plants. This study emphasizes that the performance of MSI reconstruction models could benefit from an optimized loss function and the intermediate step of ncRGB image preparation. The ability of the developed models to reconstruct high-quality MSIs from low-cost ncRGB images will, in particular, promote the application for plant phenotyping in precision agriculture. Numéro de notice : A2022-210 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14051272 Date de publication en ligne : 05/03/2022 En ligne : https://doi.org/10.3390/rs14051272 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100033
in Remote sensing > vol 14 n° 5 (March-1 2022) . - n° 1272;[article]Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions / Joseph Gesnouin (2022)
Titre : Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions Titre original : Analyse des mouvements et gestes des piétons via caméra embarquée pour la prédiction de leurs intentions Type de document : Thèse/HDR Auteurs : Joseph Gesnouin, Auteur ; Fabien Moutarde, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2022 Importance : 171 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de doctorat de l'Université Paris Sciences et Lettres, Préparée à MINES ParisTech, Spécialité
Informatique temps réel, robotique et automatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par réseau neuronal récurrent
[Termes IGN] estimation de pose
[Termes IGN] image RVB
[Termes IGN] instrument embarqué
[Termes IGN] navigation autonome
[Termes IGN] piéton
[Termes IGN] reconnaissance de gestes
[Termes IGN] réseau neuronal de graphes
[Termes IGN] squelettisation
[Termes IGN] trajectoire (véhicule non spatial)
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The autonomous vehicle (AV) is a major challenge for the mobility of tomorrow. Progress is being made every day to achieve it; however, many problems remain to be solved to achieve a safe outcome for the most vulnerable road users (VRUs). One of the major challenge faced by AVs is the ability to efficiently drive in urban environments. Such a task requires interactions between autonomous vehicles and VRUs to resolve traffic ambiguities. In order to interact with VRUs, AVs must be able to understand their intentions and predict their incoming actions. In this dissertation, our work revolves around machine learning technology as a way to understand and predict human behaviour from visual signals and more specifically pose kinematics. Our goal is to propose an assistance system to the AV that is lightweight, scene-agnostic that could be easily implemented in any embedded devices with real-time constraints. Firstly, in the gesture and action recognition domain, we study and introduce different representations for pose kinematics, based on deep learning models as a way to efficiently leverage their spatial and temporal components while staying in an euclidean grid-space. Secondly, in the autonomous driving domain, we show that it is possible to link the posture, the walking attitude and the future behaviours of the protagonists of a scene without using the contextual information of the scene (zebra crossing, traffic light...). This allowed us to divide by a factor of 20 the inference speed of existing approaches for pedestrian intention prediction while keeping the same prediction robustness. Finally, we assess the generalization capabilities of pedestrian crossing predictors and show that the classical train-test sets evaluation for pedestrian crossing prediction, i.e., models being trained and tested on the same dataset, is not sufficient to efficiently compare nor conclude anything about their applicability in a real-world scenario. To make the research field more sustainable and representative of the real advances to come. We propose new protocols and metrics based on uncertainty estimates under domain-shift in order to reach the end-goal of pedestrian crossing behavior predictors: vehicle implementation. Note de contenu : 1- Introduction
2- Human activity recognition with pose-driven deep learning models
3- From action recognition to pedestrian discrete intention prediction
4- Assessing the generalization of pedestrian crossing predictors
5- ConclusionNuméro de notice : 24066 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique temps réel, robotique et automatique : Paris Sciences et Lettres : 2022 DOI : sans En ligne : https://tel.hal.science/tel-03813520 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102091 Interactive semantic segmentation of aerial images with deep neural networks / Gaston Lenczner (2022)
Titre : Interactive semantic segmentation of aerial images with deep neural networks Type de document : Thèse/HDR Auteurs : Gaston Lenczner, Auteur ; Guy Le Besnerais, Directeur de thèse Editeur : Bures-sur-Yvette : Université Paris-Saclay Année de publication : 2022 Importance : 120 p. Format : 21 x 30 cm Note générale : Bibliographie
Thèse pour obtenir le grade de Docteur de l'Université Paris-Saclay, Spécialité : Traitement du signal et des imagesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] image aérienne
[Termes IGN] image RVB
[Termes IGN] programme interactif
[Termes IGN] réalité de terrain
[Termes IGN] réseau neuronal profond
[Termes IGN] segmentation sémantiqueIndex. décimale : THESE Thèses et HDR Résumé : (Auteur) Nous proposons dans cette thèse de mettre en place une collaboration entre un réseau de neurones profond et un utilisateur pour collecter rapidement des cartes de segmentation sémantiques précises d'images de télédétection. En bref, l'utilisateur interagit de manière itérative avec le réseau pour corriger ses prédictions initialement erronées. Concrètement, ces interactions sont des annotations représentant les labels sémantiques. Nos contributions se décomposent en quatre parties. Premièrement, nous proposons deux schémas d'apprentissage interactif pour intégrer les entrées de l'utilisateur dans les réseaux de neurones profonds. Le premier concatène les annotations de l'utilisateur avec les autres entrées du réseau (comme l'image RGB). Nous l'appliquons à la fois aux architectures convolutionnelles et aux Transformers. La seconde utilise les annotations comme une vérité terrain partielle pour ré-entraîner le réseau. Ensuite, nous proposons une stratégie d'apprentissage actif pour guider l'utilisateur vers les zones les plus pertinentes à annoter. Dans ce but, nous adaptons différentes fonctions d'acquisition issues de l'état de l'art pour évaluer l'incertitude du réseau de neurones. Enfin, nous proposons de modifier l'espace de sortie de l'algorithme pour l'adapter rapidement à de nouvelles classes sous faible supervision. Pour atténuer les problèmes de décalage de la classe d'arrière plan et d'oubli catastrophique inhérents à ce problème, nous comparons différentes régularisations et tirons parti d'une stratégie dite de pseudo-labeling. À travers des expériences sur plusieurs jeux de données de télédétection, nous démontrons l'efficacité et analysons les méthodes proposées. La combinaison de ces différents travaux aboutit à un framework robuste et polyvalent pour corriger de manière interactive les cartes de segmentation sémantique produites par des algorithmes d'apprentissage profond en télédétection. Note de contenu : Chapter 1. Introduction
1.1 Context
1.2 Open research questions
1.3 Contributions
1.4 Manuscript outline
1.5 Publications
Chapter 2. Related work
2.1 Understanding the stakes
2.2 Interactive learning
2.3 Metrics & datasets
Chapter 3. Fast interactive learning
3.1 Motivation & contribution
3.2 DISIR : Deep Image Segmentation with Interactive Refinements
3.3 Evaluation process
3.4 Experiments
3.5 Conclusion
Chapter 4. Interactive learning at scale
4.1 Transformers for a better propagation of the annotations
4.2 DISCA : Deep Image Segmentation with Continual Adaptation
Chapter 5. Guiding the interactions
5.1 Motivation & contributions
5.2 DIAL : Deep Interactive and Active Learning
5.3 Experiments
5.4 Conclusion
Chapter 6. Towards interactive class-incremental segmentation
6.1 Motivation & contributions
6.2 Methodology
6.3 Experiments
6.4 Conclusion
Chapter 7. Conclusion
7.1 Summary of contributions
7.2 Future worksNuméro de notice : 26906 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Traitement du signal et des images : Paris-Saclay : 2022 Organisme de stage : Département Traitement de l’Information et Systèmes DTIS (ONERA) nature-HAL : Thèse DOI : sans Date de publication en ligne : 14/10/2022 En ligne : https://tel.hal.science/tel-03814978 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101918
Titre : Scene understanding and gesture recognition for human-machine interaction Type de document : Thèse/HDR Auteurs : Naina Dhingra, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2022 Note générale : Bibliographie
A dissertation submitted to attain the degree of Doctor of Sciences of ETH ZurichLangues : Français (fre) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification orientée objet
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] compréhension de l'image
[Termes IGN] image RVB
[Termes IGN] interaction homme-machine
[Termes IGN] oculométrie
[Termes IGN] reconnaissance automatique
[Termes IGN] reconnaissance de formes
[Termes IGN] reconnaissance de gestes
[Termes IGN] réseau neuronal récurrent
[Termes IGN] scène
[Termes IGN] vision par ordinateurRésumé : (auteur) Scene understanding and gesture recognition are useful for a myriad of applications such as human-robotic interaction, assisting blind and visually impaired people, advanced driver assistance systems, and autonomous driving. To work autonomously in real-world environments, automatic systems need to deliver non-verbal information to enhance the verbal communication in particular for blind people. We are exploring the holistic approach for providing the scene as well as gesture related information. We propose that incorporating attention mechanisms in neural networks which behave similarly to attention in the human brain, and conducting an integrated study using neural networks in real-time can yield significant improvements in the scene and gesture understanding, thereby enhancing the user experience. In this thesis, we investigate the understanding of visual scenes and gestures. We explore these two areas, in particular, by proposing novel architectures, training methods, user studies, and thorough evaluations. We show that, for deep learning approaches, attention or self attention mechanisms improve and push the boundaries of network performance for different tasks in consideration. We suggest that the various kinds of gestures can complement and supplement each other’s information to better understand non-verbal conversation; hence integrated gestures comprehension is useful. First, we focus on visual scene understanding using scene graph generation. We propose, BGT-Net, a new network that uses an object detection model with 1) bidirectional gated recurrent units for object-object communication and 2) transformer encoders including self attention to classify the objects and their relationships. We address the problem of bias caused by the long tailed distribution in the dataset. This enables the network to perform even for the unseen objects or relationships in the dataset. Second, we propose to learn hand gesture recognition from RGB and RGB-D videos using attention learning. We present a novel architecture based on residual connections and an attention mechanism. Our approach successfully detects hand gestures when evaluated on three open-source datasets. Third, we explore pointing gesture recognition and localization using open-source software, i.e. OpenPtrack which uses a deep learning based iii network to track multi-persons in the scene. We use a Kinect sensor as an input device and conduct a user study with 26 users to evaluate the system using two setup types. Fourth, we propose a technique to perform eye gaze tracking using OpenFace which is based on a deep learning model and RGB webcam. We use support vector machine regression to estimate the position of eye gaze on the screen. In a study, we evaluate the system with 28 users and show that this system can perform similarly to commercially expensive eye trackers. Finally, we focus on 3D head pose estimation using two models: 1)headPosr includes residual connections for the base network followed by a transformer encoder. It outperforms existing models but has a drawback of being computationally expensive; 2) lwPosr uses depthwise separable convolutions and transformer encoders. It is a two stream network in fine-grained fashion to estimate the three angles of the head pose. We demonstrate that this method is able to predict head poses better than state-of-the-art lightweight networks. Note de contenu : 1- Introduction
2- Background
3- State of the art
4- Scene graph generation
5- 3D hand gesture recognition
6- Pointing gesture recognition
7- Eye-gaze tracking
8- Head pose estimation
9- Lightweight head pose estimation
10- SummaryNuméro de notice : 24039 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse étrangère Note de thèse : PhD Thesis : Sciences : ETH Zurich :2022 DOI : sans En ligne : https://www.research-collection.ethz.ch/handle/20.500.11850/559347 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101876
Titre : Vegetation index and dynamics Type de document : Monographie Auteurs : Eusebio Cano Carmona, Éditeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2022 Importance : 350 p. ISBN/ISSN/EAN : 978-1-83969-385-4 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse spatiale
[Termes IGN] analyse spectrale
[Termes IGN] Autocad Map
[Termes IGN] carte de la végétation
[Termes IGN] changement d'utilisation du sol
[Termes IGN] Colombie
[Termes IGN] couvert forestier
[Termes IGN] dynamique de la végétation
[Termes IGN] écosystème urbain
[Termes IGN] flore endémique
[Termes IGN] image aérienne
[Termes IGN] image captée par drone
[Termes IGN] image RVB
[Termes IGN] Inde
[Termes IGN] indice de diversité
[Termes IGN] indice de végétation
[Termes IGN] milieu urbain
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] outil d'aide à la décision
[Termes IGN] Pakistan
[Termes IGN] pédologie locale
[Termes IGN] Pennsylvanie (Etats-Unis)
[Termes IGN] Pinus sylvestris
[Termes IGN] système d'information géographique
[Termes IGN] traitement d'imageIndex. décimale : 35.41 Applications de télédétection - végétation Résumé : (Editeur) The book contemplates different ways of approaching the study of vegetation as well as the type of indices to be used. However, all the works pursue the same objective: to know and interpret nature from different points of view, either through knowledge of nature in situ or the use of technology and mapping using satellite images. Chapters analyze the ecological parameters that affect vegetation, the species that make up plant communities, and the influence of humans on vegetation. Note de contenu : 1. Introductory Chapter: Methodological Aspects for the Study of Vegetation / Eusebio Cano Carmona, Ricardo Quinto Canas, Ana Cano Ortiz and Carmelo María Musarella
2. Using GIS and the Diversity Indices: A Combined Approach to Woody Plant Diversity in the Urban Landscape / Tuba Gül Doğan and Engin Eroğlu
3. Classical and Modern Remote Mapping Methods for Vegetation Cover / Algimantas Česnulevičius, Artūras Bautrėnas, Linas Bevainis and Donatas Ovodas
4. Assessment of the State of Forest Plant Communities of Scots Pine (Pinus sylvestris L.) in the Conditions of Urban Ecosystems / Elena Runova, Vera Savchenkova, Ekaterina Demina-Moskovskaya and Anastasia Baranenkova
5. Landscape Genetics and Phytogeography of Criollo Avocadoes Persea americana from Northeast Colombia / Clara Inés Saldamando-Benjumea, Gloria Patricia Cañas-Gutiérrez, Jorge Muñoz and Rafael Arango Isaza
6. The Use of NDVI and NDBI to Provide Subsidies to Public Manager’s Decision Making on Maintaining the Thermal Comfort in Urban Areas / Arthur Santos, Fernando Santil and Claudionor Silva
7. Detailed Investigation of Spectral Vegetation Indices for Fine Field-Scale Phenotyping / Maria Polivova and Anna Brook
8. Predictive Models for Reforestation and Agricultural Reclamation: A Clearfield County, Pennsylvania Case Study / Zhi Yue and Jon Bryan Burley
9. Dynamic-Catenal Phytosociology for Evaluating Vegetation / Sara del Río, Raquel Alonso-Redondo, Alejandro González-Pérez, Aitor Álvarez-Santacoloma, Giovanni Breogán Ferreiro Lera and Ángel Penas
10. Germination and Seedling Growth of Entandrophragma bussei Harms ex Engl. from Wild Populations / Samora M. Andrew, Siwa A. Kombo and Shabani A.O. Chamshama
11. Spatial Dynamics of Forest Cover and Land Use Changes in the Western Himalayas of Pakistan / Amjad ur Rahman, Esra Gürbüz, Semih Ekercin and Shujaul Mulk Khan
12. Understanding Past and Present Vegetation Dynamics Using the Palynological Approach: An Introductory Discourse / Sylvester Onoriode Obigba
13. Forest Vegetation and Dynamics Studies in India / Madan Prasad Singh, Manohara Tattekere Nanjappa, Sukumar Raman, Suresh Hebbalalu Satyanatayana, Ayyappan Narayanan, Ganesan Renagaian and Sreejith Kalpuzha Ashtamoorthy
14. Photosynthetic Antenna Size Regulation as an Essential Mechanism of Higher Plants Acclimation to Biotic and Abiotic Factors: The Role of the Chloroplast Plastoquinone Pool and Hydrogen Peroxide / Maria M. Borisova-Mubarakshina, Ilya A. Naydov, Daria V. Vetoshkina, Marina A. Kozuleva, Daria V. Vilyanen, Natalia N. Rudenko and Boris N. Ivanov
15. Rockbee Repellent Endemic Plant Species of Andaman-Nicobar Archipelago in the Bay of Bengal / Sam Paul Mathew and Raveendranpillai Prakashkumar
16. Evaluating Insects as Bioindicators of the Wetland Environment Quality (Arid Region of Algeria) / Brahimi Djamel, Rahmouni Abdelkader, Brahimi Abdelghani and Mesli LotfiNuméro de notice : 26797 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.87465 Date de publication en ligne : 23/02/2022 En ligne : https://doi.org/10.5772/intechopen.87465 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100059 Building detection with convolutional networks trained with transfer learning / Simon Šanca in Geodetski vestnik, vol 65 n° 4 (December 2021 - February 2022)PermalinkFeature matching for multi-epoch historical aerial images: A new pipeline feature detection pipeline in open-source MicMac / Lulin Zhang in Blog de la RFPT, sans n° ([17/11/2021])PermalinkFeature matching for multi-epoch historical aerial images / Lulin Zhang in ISPRS Journal of photogrammetry and remote sensing, Vol 182 (December 2021)PermalinkA deep multi-modal learning method and a new RGB-depth data set for building roof extraction / Mehdi Khoshboresh Masouleh in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 10 (October 2021)PermalinkCNN-based RGB-D salient object detection: Learn, select, and fuse / Hao Chen in International journal of computer vision, vol 129 n° 7 (July 2021)PermalinkRemote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space / Min Wu in The Visual Computer, vol 37 n° 7 (July 2021)PermalinkSemantic unsupervised change detection of natural land cover with multitemporal object-based analysis on SAR images / Donato Amitrano in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 7 (July 2021)PermalinkAssessing forest phenology: A multi-scale comparison of near-surface (UAV, spectral reflectance sensor, PhenoCam) and satellite (MODIS, Sentinel-2) remote sensing / Shangharsha Thapa in Remote sensing, vol 13 n° 8 (April-2 2021)PermalinkVisual positioning in indoor environments using RGB-D images and improved vector of local aggregated descriptors / Longyu Zhang in ISPRS International journal of geo-information, vol 10 n° 4 (April 2021)PermalinkMulti-level progressive parallel attention guided salient object detection for RGB-D images / Zhengyi Liu in The Visual Computer, vol 37 n° 3 (March 2021)Permalink