Descripteur
Termes IGN > sciences naturelles > physique > traitement d'image > analyse d'image numérique > analyse d'image orientée objet > détection d'objet
détection d'objetVoir aussi |
Documents disponibles dans cette catégorie (100)
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
Application of machine learning techniques for evidential 3D perception, in the context of autonomous driving / Edouard Capellier (2020)
Titre : Application of machine learning techniques for evidential 3D perception, in the context of autonomous driving Type de document : Thèse/HDR Auteurs : Edouard Capellier, Auteur ; Véronique Berge-Cherfaoui, Directeur de thèse ; Franck Davoine, Directeur de thèse Editeur : Compiègne : Université de Technologie de Compiègne UTC Année de publication : 2020 Importance : 123 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée pour l'obtention du grade de Docteur de l'UTC, Robotique et Sciences et Technologies de l'Information et des SystèmesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage profond
[Termes IGN] carte routière
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection d'objet
[Termes IGN] données lidar
[Termes IGN] image RVB
[Termes IGN] intelligence artificielle
[Termes IGN] navigation autonome
[Termes IGN] segmentation sémantique
[Termes IGN] théorie de Dempster-Shafer
[Termes IGN] vision par ordinateur
[Termes IGN] visualisation 3DIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The perception task is paramount for self-driving vehicles. Being able to extract accurate and significant information from sensor inputs is mandatory, so as to ensure a safe operation. The recent progresses of machine-learning techniques revolutionize the way perception modules, for autonomous driving, are being developed and evaluated, while allowing to vastly overpass previous state-of-the-art results in practically all the perception-related tasks. Therefore, efficient and accurate ways to model the knowledge that is used by a self-driving vehicle is mandatory. Indeed, self-awareness, and appropriate modeling of the doubts, are desirable properties for such system. In this work, we assumed that the evidence theory was an efficient way to finely model the information extracted from deep neural networks. Based on those intuitions, we developed three perception modules that rely on machine learning, and the evidence theory. Those modules were tested on real-life data. First, we proposed an asynchronous evidential occupancy grid mapping algorithm, that fused semantic segmentation results obtained from RGB images, and LIDAR scans. Its asynchronous nature makes it particularly efficient to handle sensor failures. The semantic information is used to define decay rates at the cell level, and handle potentially moving object. Then, we proposed an evidential classifier of LIDAR objects. This system is trained to distinguish between vehicles and vulnerable road users, that are detected via a clustering algorithm. The classifier can be reinterpreted as performing a fusion of simple evidential mass functions. Moreover, a simple statistical filtering scheme can be used to filter outputs of the classifier that are incoherent with regards to the training set, so as to allow the classifier to work in open world, and reject other types of objects. Finally, we investigated the possibility to perform road detection in LIDAR scans, from deep neural networks. We proposed two architectures that are inspired by recent state-of-the-art LIDAR processing systems. A training dataset was acquired and labeled in a semi-automatic fashion from road maps. A set of fused neural networks reaches satisfactory results, which allowed us to use them in an evidential road mapping and object detection algorithm, that manages to run at 10 Hz Note de contenu : 1- Introduction
2- Machine learning for perception in autonomous driving
3- The evidence theory, and its applications in autonomous driving
4- A synchronous evidential grid mapping from RGB images and LIDAR scans
5- Evidential LIDAR object classification
6- Road detection in LIDAR scans
7- Application of RoadSeg:evidential road surface mapping
8- ConclusionNuméro de notice : 25895 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Robotique et Sciences et Technologies de l'Information et des Systèmes : UTC : 2020 Organisme de stage : Laboratoire Heudiasyc nature-HAL : Thèse DOI : sans En ligne : https://hal.science/tel-02897810v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96013 Cattle detection and counting in UAV images based on convolutional neural networks / Wen Shao in International Journal of Remote Sensing IJRS, vol 41 n° 1 (01 - 08 janvier 2020)
[article]
Titre : Cattle detection and counting in UAV images based on convolutional neural networks Type de document : Article/Communication Auteurs : Wen Shao, Auteur ; Rei Kawakami, Auteur ; Ryota Yoshihashi, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 31 - 52 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] bovin
[Termes IGN] chevauchement
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] comptage
[Termes IGN] détection d'objet
[Termes IGN] image captée par drone
[Termes IGN] modélisation 3DRésumé : (auteur) For assistance with grazing cattle management, we propose a cattle detection and counting system based on Convolutional Neural Networks (CNNs) using aerial images taken by an Unmanned Aerial Vehicle (UAV). To improve detection performance, we take advantage of the fact that, with UAV images, the approximate size of the objects can be predicted when the UAV’s height from the ground can be assumed to be roughly constant. We resize an image to be fed into the CNN to an optimum resolution determined by the object size and the down-sampling rate of the network, both in training and testing. To avoid repetition of counting in images that have large overlaps to adjacent ones and to obtain the accurate number of cattle in an entire area, we utilize a three-dimensional model reconstructed by the UAV images for merging the detection results of the same target. Experiments show that detection performance is greatly improved when using the optimum input resolution with an F-measure of 0.952, and counting results are close to the ground truths when the movement of cattle is approximately stationary compared to that of the UAV’s. Numéro de notice : A2020-209 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431161.2019.1624858 Date de publication en ligne : 11/06/2019 En ligne : https://doi.org/10.1080/01431161.2019.1624858 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94891
in International Journal of Remote Sensing IJRS > vol 41 n° 1 (01 - 08 janvier 2020) . - pp 31 - 52[article]Context-aware convolutional neural network for object detection in VHR remote sensing imagery / Yiping Gong in IEEE Transactions on geoscience and remote sensing, vol 58 n° 1 (January 2020)
[article]
Titre : Context-aware convolutional neural network for object detection in VHR remote sensing imagery Type de document : Article/Communication Auteurs : Yiping Gong, Auteur ; Zhifeng Xiao, Auteur ; Xiaowei Tan, Auteur Année de publication : 2020 Article en page(s) : pp 34 - 44 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] description multiniveau
[Termes IGN] détection d'objet
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image à très haute résolution
[Termes IGN] prise en compte du contexte
[Termes IGN] vision par ordinateur
[Termes IGN] zone d'intérêtRésumé : (auteur) Object detection in very-high-resolution (VHR) remote sensing imagery remains a challenge. Environmental factors, such as illumination intensity and weather, reduce image quality, resulting in poor feature representation and limited detection accuracy. To enrich the feature representation and mine the underlying context information among objects, this article proposes a context-aware convolutional neural network (CA-CNN) model for object detection that includes proposal generation, context feature extraction, feature fusion, and classification. During feature extraction, we propose integrating a context-regions-of-interests (Context-RoIs) mining layer into the CNN model and extracting context features by mapping Context-RoIs mined from the foreground proposals to multilevel feature maps. Finally, the context features extracted from multilevel layers are fused into a single layer, and the proposals represented by the fused features are classified by a softmax classifier. In this article, through numerous experiments, we thoroughly explore the influence of key factors, such as Context-RoIs, different feature scales, and different spatial context window sizes. Because of the end-to-end network design approach, our proposed model simultaneously maintains high efficiency and effectiveness. We conducted all model testing on the public NWPU VHR-10 data set. The experimental results demonstrate that our proposed CA-CNN model achieves significantly improved model performance and better detection results compared with the state-of-the-art methods. Numéro de notice : A2020-038 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2930246 Date de publication en ligne : 23/09/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2930246 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94492
in IEEE Transactions on geoscience and remote sensing > vol 58 n° 1 (January 2020) . - pp 34 - 44[article]
Titre : Convolutional Neural Networks for embedded vision Titre original : Réseaux de neurones CNN pour la vision embarquée Type de document : Thèse/HDR Auteurs : Lucas Fernandez Brillet, Auteur ; Stéphane Mancini, Directeur de thèse Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2020 Importance : 164 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de l'Université Grenoble Alpes, Spécialité : Mathématiques, sciences et technologies de
l’information, informatiqueLangues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse en composantes principales
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] compression d'image
[Termes IGN] détection d'objet
[Termes IGN] image à haute résolution
[Termes IGN] instrument embarqué
[Termes IGN] vision par ordinateur
[Termes IGN] zone d'intérêtIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Recently, Convolutional Neural Networks have become the state-of-the-art soluion(SOA) to most computer vision problems. In order to achieve high accuracy rates, CNNs require a high parameter count, as well as a high number of operations. This greatly complicates the deployment of such solutions in embedded systems, which strive to reduce memory size. Indeed, while most embedded systems are typically in the range of a few KBytes of memory, CNN models from the SOA usually account for multiple MBytes, or even GBytes in model size. Throughout this thesis, multiple novel ideas allowing to ease this issue are proposed. This requires to jointly design the solution across three main axes: Application, Algorithm and Hardware.In this manuscript, the main levers allowing to tailor computational complexity of a generic CNN-based object detector are identified and studied. Since object detection requires scanning every possible location and scale across an image through a fixed-input CNN classifier, the number of operations quickly grows for high-resolution images. In order to perform object detection in an efficient way, the detection process is divided into two stages. The first stage involves a region proposal network which allows to trade-off recall for the number of operations required to perform the search, as well as the number of regions passed on to the next stage. Techniques such as bounding box regression also greatly help reduce the dimension of the search space. This in turn simplifies the second stage, since it allows to reduce the task’s complexity to the set of possible proposals. Therefore, parameter counts can greatly be reduced.Furthermore, CNNs also exhibit properties that confirm their over-dimensionment. This over-dimensionement is one of the key success factors of CNNs in practice, since it eases the optimization process by allowing a large set of equivalent solutions. However, this also greatly increases computational complexity, and therefore complicates deploying the inference stage of these algorithms on embedded systems. In order to ease this problem, we propose a CNN compression method which is based on Principal Component Analysis (PCA). PCA allows to find, for each layer of the network independently, a new representation of the set of learned filters by expressing them in a more appropriate PCA basis. This PCA basis is hierarchical, meaning that basis terms are ordered by importance, and by removing the least important basis terms, it is possible to optimally trade-off approximation error for parameter count. Through this method, it is possible to compress, for example, a ResNet-32 network by a factor of ×2 both in the number of parameters and operations with a loss of accuracy Note de contenu : Introduction
1- Deep learning overview
2- Methodology to adapt the computational complexity of CNN-based object detection for efficient inference in an applicative use-case
3- CNN compression
4- Cascaded and compressed CNNs for fast and lightweight face detection
5- Hardware evaluation on embedded multiprocessor
Thesis Conclusion & PerspectivesNuméro de notice : 28392 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Mathématiques, sciences et technologies de l’information, informatique : Grenoble : 2020 DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03101523/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98739 Détection et vectorisation automatiqued’objets linéaires dans des nuages de points de voirie / Etienne Barçon (2020)
Titre : Détection et vectorisation automatiqued’objets linéaires dans des nuages de points de voirie Type de document : Mémoire Auteurs : Etienne Barçon, Auteur Editeur : Strasbourg : Institut National des Sciences Appliquées INSA Strasbourg Année de publication : 2020 Importance : 110 p. Format : 21 x 30 cm Note générale : bibliographie
Mémoire de fin d'études d'Ingénieur INSA, spécialité TopographieLangues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] corrélation croisée normalisée
[Termes IGN] détection automatique
[Termes IGN] détection d'objet
[Termes IGN] détection de contours
[Termes IGN] données lidar
[Termes IGN] polyligne
[Termes IGN] réseau routier
[Termes IGN] segmentation
[Termes IGN] semis de points
[Termes IGN] seuillage d'image
[Termes IGN] trottoir
[Termes IGN] vectorisationIndex. décimale : INSAS Mémoires d'ingénieur de l'INSA Strasbourg - Topographie, ex ENSAIS Résumé : (auteur) Ce mémoire présente une méthode de détection automatique des marquages et des glissières dans un environnement autoroutier, à partir d'un nuage de points. L'approche employée utilise essentiellement des outils de traitement d'images. Le nuage de points est converti en images d’intensité et images d’altitudes par une projection verticale sur un plan. La détection des marquages au sol est effectuée par seuillage des images d’intensité. La détection des glissières s’effectue en plusieurs temps, une détection des objets linéaires en 2D puis une vectorisation 3D à partir de profils, à l’aide des images d’altitudes. Les résultats obtenus sont convaincants bien que perfectibles. La méthode mise en place est jugée généralisable à d’autres objets comme les murs et les bordures de trottoir. Note de contenu : Introduction
1- Etat de l'art
2- Développements
3- Résultats obtenus et analyse
4- Perspectives d'améliorations
ConclusionNuméro de notice : 28517 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Mémoire ingénieur INSAS Organisme de stage : TT Géomètres-Experts (Paris) DOI : sans En ligne : http://eprints2.insa-strasbourg.fr/4144/ Format de la ressource électronique : url Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97292 PermalinkImage processing applications in object detection and graph matching: from Matlab development to GPU framework / Beibei Cui (2020)PermalinkPermalinkPermalinkReconnaissance automatique d’objets pour le jumeau numérique ferroviaire à partir d’imagerie aérienne / Valentin Desbiolles (2020)PermalinkPermalinkPermalinkShip identification and characterization in Sentinel-1 SAR images with multi-task deep learning / Clément Dechesne in Remote sensing, Vol 11 n° 24 (December-2 2019)PermalinkHalf a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning / Benjamin Kellenberger in IEEE Transactions on geoscience and remote sensing, vol 57 n° 12 (December 2019)PermalinkSig-NMS-based faster R-CNN combining transfer learning for small target detection in VHR optical remote sensing imagery / Ruchan Dong in IEEE Transactions on geoscience and remote sensing, vol 57 n° 11 (November 2019)Permalink