Descripteur
Documents disponibles dans cette catégorie (14)
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
Titre : Reshaping perception for autonomous driving with semantic keypoints Type de document : Thèse/HDR Auteurs : Lorenzo Bertoni, Auteur Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2022 Importance : 177 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée pour l'obtention du grade de Docteur ès Sciences, Ecole Polytechnique Fédérale de LausanneLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection automatique
[Termes IGN] détection d'objet
[Termes IGN] détection de piéton
[Termes IGN] estimation de pose
[Termes IGN] navigation autonome
[Termes IGN] système multi-agents
[Termes IGN] vision par ordinateurRésumé : (auteur) The field of artificial intelligence is set to fuel the future of mobility by driving forward the transition from advanced driver-assist systems to fully autonomous vehicles (AV). Yet the current technology, backed by cutting-edge deep learning techniques, still leads to fatal accidents and does not convey trust. Current frameworks for 3D perception tasks, such as 3D object detection, are not adequate as they (i) do not generalize well to new scenarios, (ii) do not take into account measures of confidence in their predictions, and (iii) are not suitable for large-scale deployment as mainly based on costly LiDAR sensors. This doctoral thesis aims to study vision-based deep learning frameworks that can accurately perceive the world in 3D and generalize to new scenarios. We propose to escape the pixel domain using semantic keypoints, a sparse representation for every object in the scene containing meaningful information for 2D and 3D reasoning. The low-dimensionality enables downstream neural networks to focus on essential elements in the scene and improve their generalization capabilities. Furthermore, driven by the limitation of deep learning architectures outputting point estimates, we study how to estimate a confidence interval for each prediction. In particular, we emphasize vulnerable road users, such as pedestrians and cyclists, and explicitly address the long tail of 3D pedestrian detection to contribute to the safety of our roads. We further show the efficacy of our framework on multiple real-world domains by (a) integrating it in an existing AV pipeline, (b) detecting human-robot eye contact in real-world scenarios, and (c) helping verify the compliance of safety measures in the case of the COVID-19 outbreak. Finally, we publicly release the source code of all our projects and develop a unified library to contribute to an open science mission. Note de contenu : 1- Introduction
2- Semantic keypoints detection
3- Monocular 3D pedestrian localization and uncertainty estimation
4- Tackling the long tail of 3D pedestrian localization with stereo cameras
5- Autonomous driving applications of pedestrian 3D detection
6- Detecting pedestrians attention: Human-robot eye contact in the wild
7- Beyond autonomous driving: Social interactions and social distancing
8- ConclusionNuméro de notice : 24077 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse étrangère Note de thèse : PhD Thesis : Sciences : EPFL : 2022 DOI : 10.5075/epfl-thesis-10072 En ligne : https://doi.org/10.5075/epfl-thesis-10072 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102212 A shape transformation-based dataset augmentation framework for pedestrian detection / Zhe Chen in International journal of computer vision, vol 129 n° 4 (April 2021)
[article]
Titre : A shape transformation-based dataset augmentation framework for pedestrian detection Type de document : Article/Communication Auteurs : Zhe Chen, Auteur ; Wanli Ouyang, Auteur ; Tongliang Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1121 - 1138 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage par transformation
[Termes IGN] apprentissage profond
[Termes IGN] déformation d'objet
[Termes IGN] détection de piéton
[Termes IGN] jeu de données
[Termes IGN] synthèse d'image
[Termes IGN] vision par ordinateurRésumé : (auteur) Deep learning-based computer vision is usually data-hungry. Many researchers attempt to augment datasets with synthesized data to improve model robustness. However, the augmentation of popular pedestrian datasets, such as Caltech and Citypersons, can be extremely challenging because real pedestrians are commonly in low quality. Due to the factors like occlusions, blurs, and low-resolution, it is significantly difficult for existing augmentation approaches, which generally synthesize data using 3D engines or generative adversarial networks (GANs), to generate realistic-looking pedestrians. Alternatively, to access much more natural-looking pedestrians, we propose to augment pedestrian detection datasets by transforming real pedestrians from the same dataset into different shapes. Accordingly, we propose the Shape Transformation-based Dataset Augmentation (STDA) framework. The proposed framework is composed of two subsequent modules, i.e. the shape-guided deformation and the environment adaptation. In the first module, we introduce a shape-guided warping field to help deform the shape of a real pedestrian into a different shape. Then, in the second stage, we propose an environment-aware blending map to better adapt the deformed pedestrians into surrounding environments, obtaining more realistic-llooking pedestrians and more beneficial augmentation results for pedestrian detection. Extensive empirical studies on different pedestrian detection benchmarks show that the proposed STDA framework consistently produces much better augmentation results than other pedestrian synthesis approaches using low-quality pedestrians. By augmenting the original datasets, our proposed framework also improves the baseline pedestrian detector by up to 38% on the evaluated benchmarks, achieving state-of-the-art performance. Numéro de notice : A2021-354 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s11263-020-01412-0 Date de publication en ligne : 09/01/2021 En ligne : https://doi.org/10.1007/s11263-020-01412-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97606
in International journal of computer vision > vol 129 n° 4 (April 2021) . - pp 1121 - 1138[article]Lightweight convolutional neural network-based pedestrian detection and re-identification in multiple scenarios / Xiao Ke in Machine Vision and Applications, vol 32 n° 2 (March 2021)
[article]
Titre : Lightweight convolutional neural network-based pedestrian detection and re-identification in multiple scenarios Type de document : Article/Communication Auteurs : Xiao Ke, Auteur ; Xinru Lin, Auteur ; Liyun Qin, Auteur Année de publication : 2021 Article en page(s) : n° 46 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] comportement
[Termes IGN] détection de piéton
[Termes IGN] objet mobile
[Termes IGN] reconnaissance de formes
[Termes IGN] vision par ordinateurRésumé : (auteur) Pedestrian detection and re-identification technology is a research hotspot in the field of computer vision. This technology currently has issues such as insufficient pedestrian expression ability, occlusion, diverse pedestrian attitude, and difficulty of small-scale pedestrian detection. In this paper, we proposed an end-to-end pedestrian detection and re-identification model in real scenes, which can effectively solve these problems. In our model, the original images are processed with a non-overlapped image blocking data augmentation method, and then input them into the YOLOv3 detector to obtain the object position information. LCNN-based pedestrian re-identification model is used to extract the features of the object. Furthermore, the eigenvectors of the object and the detected pedestrians are calculated, and the similarity between them are used to determine whether they can be marked as target pedestrians. Our method is lightweight and end-to-end, which can be applied to the real scenes. Numéro de notice : A2021-455 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01169-7 Date de publication en ligne : 24/02/2021 En ligne : https://doi.org/10.1007/s00138-021-01169-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97900
in Machine Vision and Applications > vol 32 n° 2 (March 2021) . - n° 46[article]
Titre : WeCount, le trafic compté par les citoyens Type de document : Mémoire Auteurs : Victor Oxombre, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2020 Importance : 34 p. Format : 21 x 30 cm Note générale : Bibliographie
Rapport de projet pluridisciplinaire, cycle ING2Langues : Français (fre) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] bicyclette
[Termes IGN] comptage
[Termes IGN] détection d'objet
[Termes IGN] détection de piéton
[Termes IGN] Dublin (Irlande ; ville)
[Termes IGN] image infrarouge
[Termes IGN] image thermique
[Termes IGN] Raspberry Pi
[Termes IGN] temps réel
[Termes IGN] trafic routier
[Termes IGN] visualisation de donnéesIndex. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (Auteur) L’objectif principal du projet Européen WeCount est d’optimiser le processus de comptage du trafic en direct en dotant les communautés locales de capteurs à faible coût. Le projet fournira aux communautés locales de 5 villes Européennes des capteurs entièrement automatisés, appelés Telraam, capables de compter les voitures, les piétons, les vélos et les véhicules lourds. Le Spatial Dynamics Lab a pour mission d’impliquer les communautés locales dans des activités de science citoyenne avec le capteur dans les rues de Dublin. Mon superviseur Mr Francesco PILLA, le directeur du laboratoire, souhaite apporter des améliorations sur le capteur. Ces modifications permettront d’avoir un comptage durant la journée et la nuit, et une meilleure qualité de comptage. Ainsi, des données plus significatives sur le trafic en direct seront envoyées au gouvernement local. Pour cela, une étude documentaire sera effectuée sur la possibilité de détecter des objets de nuit. Ensuite, la faisabilité pratique de la théorie sera étudiée. Enfin, une plate-forme de visualisation locale sera mise en place. Note de contenu : Introduction
1. Détection d’objets par la caméra et installation
1.1 Détection d’objets en vidéo
1.2 Choix de caméra
1.3 Installation du capteur
2. Comptage avec le Telraam
2.1 Détection et traçage d’objets du Telraam
2.2 Adaptation à une caméra infrarouge
2.3 Détection de nuit
3. Version locale de Kepler.gl
3.1 Principe de Kepler.gl
3.2 React et Redux
3.3 Site obtenu
ConclusionNuméro de notice : 26354 Affiliation des auteurs : non IGN Nature : Mémoire de projet pluridisciplinaire Organisme de stage : Spatial Dynamics Lab Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95785 Documents numériques
peut être téléchargé
WeCount, le trafic compté par les citoyens - pdf auteurAdobe Acrobat PDF
Titre : Ensemble methods for pedestrian detection in dense crowds Type de document : Thèse/HDR Auteurs : Jennifer Vandoni, Auteur ; Sylvie Le Hégarat-Mascle, Directeur de thèse Editeur : Paris-Orsay : Université de Paris 11 Paris-Sud Centre d'Orsay Année de publication : 2019 Importance : 182 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université Paris-Saclay, Sciences et technologies de l’information et de la communication (STIC), Spécialité : Traitement du Signal et des ImagesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] algorithme d'apprentissage
[Termes IGN] apprentissage dirigé
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] comportement
[Termes IGN] densité de population
[Termes IGN] détection de piéton
[Termes IGN] données multicapteurs
[Termes IGN] étalonnage
[Termes IGN] fusion de données
[Termes IGN] taxinomie
[Termes IGN] théorie de Dempster-ShaferIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The interest surrounding the study of crowd phenomena spanned during the last decade across multiple fields, including computer vision, physics, sociology, simulation and visualization. There are different levels of granularity at which crowd studies can be performed, namely a finer microanalysis, aimed to detect and then track each pedestrian individually; and a coarser macro-analysis, aimed to model the crowd as a whole.
One of the most difficult challenges when working with human crowds is that usual pedestrian detection methodologies do not scale well to the case where only heads are visible, for a number of reasons such as absence of background, high visual homogeneity, small size of the objects, and heavy occlusions. For this reason, most micro-analysis studies by means of pedestrian detection and tracking methodologies are performed in low to medium-density crowds, whereas macro-analysis through density estimation and people counting is more suited in presence of high-density crowds, where the exact position of each individual is not necessary. Nevertheless, in order to analyze specific events involving high-density crowds for monitoring the flow and preventing disasters such as stampedes, a complete understanding of the scene must be reached. This study deals with pedestrian detection in high-density crowds from a monocamera system, striving to obtain localized detections of all the individuals which are part of an extremely dense crowd. The detections can be then used both to obtain robust density estimation, and to initialize a tracking algorithm. In presence of difficult problems such as our application, supervised learning techniques are well suited. However, two different questions arise, namely which classifier is the most adapted for the considered environment, and which data to use to learn from. We cast the detection problem as a Multiple Classifier System (MCS), composed by two different ensembles of classifiers, the first one based on SVM (SVM-ensemble) and the second one based on CNN (CNN-ensemble), combined relying on the Belief Function Theory (BFT) designing a fusion method which is able to exploit their strengths for pixel-wise classification. SVM-ensemble is composed by several SVM detectors based on different gradient, texture and orientation descriptors, able to tackle the problem from different perspectives. BFT allows us to take into account the imprecision in addition to the uncertainty value provided by each classifier, which we consider coming from possible errors in the calibration procedure and from pixel neighbor’s heterogeneity in the image space due to the close resolution of the target (head) and
descriptor respectively. However, scarcity of labeled data for specific dense crowd contexts reflects in the impossibility to easily obtain robust training and validation sets. By exploiting belief functions directly derived
from the classifiers’ combination, we therefore propose an evidential Query-by-Committee (QBC) active learning algorithm to automatically select the most informative training samples. On the other side, we explore deep learning techniques by casting the problem as a segmentation task in presence of soft labels, with a fully convolutional network architecture designed to recover small objects (heads) thanks to a tailored use of dilated convolutions. In order to obtain a pixel-wise measure of reliability about the network’s predictions, we create a CNN-ensemble by means of dropout at inference time, and we combine the different obtained realizations in the
context of BFT. To conclude, we show that the dense output map given by the MCS can be employed not only
for pedestrian detection at microscopic level, but also to perform macroscopic analysis, bridging the gap between the two levels of granularity. We therefore finally focus our attention to people counting, proposing an evaluation method that can be applied at every scale, resulting to be more precise in the error and uncertainty evaluation (disregarding possible compensations) as well as more useful for the modeling community that could use it to improve and validate local density estimation.Note de contenu : 1- Crowd understanding
2- Supervised learning and classifier combination
3- SVM descriptors for pedestrian detection in high-density crowds
4- Taking into account imprecision with Belief Function Framework
5- Evidential QBC Active Learning
6- CNNs for pedestrian detection in high-density crowds
7- CNN-ensemble and evidential Multiple Classifier System
8- Density Estimation
ConclusionNuméro de notice : 25704 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Traitement du Signal et des Images : Paris 11 : 2019 Organisme de stage : Systèmes et applications des technologies de l'information et de l'énergie (Paris) nature-HAL : Thèse DOI : sans En ligne : https://theses.hal.science/tel-02318892/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94838 Spatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data / Michalis A. Savelonas in Computer Vision and image understanding, vol 171 (June 2018)PermalinkGenerating a hazard map of dynamic objects using lidar mobile mapping / Alexander Schlichting in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 12 (December 2016)PermalinkSimultaneous detection and tracking of pedestrian from panoramic laser scanning data / Wen Xiao in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol III-3 (July 2016)PermalinkPersonal mobility pattern mining and anomaly detection in the GPS era / Dong-He Shih in Cartography and Geographic Information Science, Vol 43 n° 1 (January 2016)PermalinkPermalinkA multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification / Z. Wang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)PermalinkUser-side adaptive protection of location privacy in participatory sensing / Becker Agir in Geoinformatica, vol 18 n° 1 (January 2014)PermalinkAutomatic detection and tracking of pedestrians from a moving stereo rig / Konrad Schindler in ISPRS Journal of photogrammetry and remote sensing, vol 65 n° 6 (November - December 2010)PermalinkFace blurring for privacy in street-level geoviewers combining face, body and skin detectors / Alexandre Devaux (20/05/2009)Permalink