Search results for "Vision par ordinateur"

showing 10 items of 14 documents

Real-time micro-expression analysis by artificial vision

2022

Human-computer interaction technologies focus more and more on the human being, whether it is on his identity, or on his physical and mental state. Significant progress has been made in the last few decades. However, the study of thoughts and emotions is still an underdeveloped field, but one that has begun to gain considerable interest. In this field, the analysis of facial expressions is the preferred treatment.Unlike a macro-expression, which is visible to the eye, a micro-expression is a type of involuntary facial expression that is extremely rapid and of very low intensity. The computer vision scientific community has been studying ways to automatically recognize micro-expressions usin…

Artificial intelligence[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingVision par ordinateurMachine learningComputer visionEmotional artificial intelligenceApprentissage automatiqueIntelligence artificielleIntelligence artificielle émotionnelle
researchProduct

Traitement de données RGB et Lidar à extrêmement haute résolution: retombées de la compétition de fusion de données 2015 de l'IEEE GRSS - Partie A / …

2016

International audience; In this paper, we discuss the scientific outcomes of the 2015 data fusion contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource studies. The 2015 edition of the contest proposed a multiresolution and multisensorial challenge involving extremely high-resolution RGB images and a three-dimensional (3-D) LiDAR point cloud. The competition was framed in two parallel tracks, considering 2-D and 3-D products, respectively. In this paper, we discuss the sci…

Atmospheric Science010504 meteorology & atmospheric sciencesComputer scienceMULTIMODAL-DATA FUSIONGeophysics. Cosmic physics0211 other engineering and technologies02 engineering and technologyCONTESTcomputer.software_genre01 natural sciencesOutcome (game theory)LIDARTraitement des imagesIMAGE ANALYSIS AND DATA FUSION (IADF)DEEP NEURAL NETWORKSDeep neural networksTraitement du signal et de l'imageMULTIRESOLUTION910 Geography & travelMultiresolutionGround truthLANDCOVER CLASSIFICATIONIMAGE AERIENNE1903 Computers in Earth SciencesBenchmarkingVision par ordinateur et reconnaissance de formesOcean engineering10122 Institute of GeographyLidarDeep neural networksData miningExtremely high spatial resolutionMultimodal-data fusionLiDARComputers in Earth Sciences; Atmospheric ScienceImage analysis and data fusion (IADF)EXTREMELY HIGH SPATIAL RESOLUTIONCLASSIFICATIONTRAITEMENT IMAGE1902 Atmospheric ScienceAPPRENTISSAGE STATISTIQUEComputers in Earth SciencesTELEDETECTIONSynthèse d'image et réalité virtuelleTC1501-1800021101 geological & geomatics engineering0105 earth and related environmental sciencesLandcover classificationmultiresolution-[INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB]QC801-809Intelligence artificielleMULTISOURCESensor fusionRGB color modelcomputerMultisource
researchProduct

Compréhension de scènes urbaines basée sur la polarisation

2021

Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying chall…

Deep LearningSegmentation[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingComputer VisionVision par ordinateurPolarimetryScene understandingDepth estimationEstimation de profondeurPolarimétrieCompréhension de scène
researchProduct

Indoor Scene Understanding using Non-Conventional Cameras

2020

Humans understand environments effortlessly, under a wide variety of conditions, by the virtue of visual perception. Computer vision for similar visual understanding is highly desirable, so that machines can perform complex tasks by interacting with the real world, to assist or entertain humans. In this regard, we are particularly interested in indoor environments, where humans spend nearly all their lifetime.This thesis specifically addresses the problems that arise during the quest of the hierarchical visual understanding of indoor scenes.On the side of sensing the wide 3D world, we propose to use non-conventional cameras, namely 360º imaging and 3D sensors. On the side of understanding, …

Intelligence artificielle - Robotique mobile - Vision par ordinateur[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Artificial IntelligenceVision par ordinateur[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Robotique mobile[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionIntelligence artificielleMobile roboticsMobile robotics - Artificial Intelligence - computer vision[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
researchProduct

Depth Attention for Scene Understanding

2022

Deep learning models can nowadays teach a machine to realize a number of tasks, even with better precision than human beings. Among all the modules of an intelligent machine, perception is the most essential part without which all other action modules have difficulties in safely and precisely realizing the target task under complex scenes. Conventional perception systems are based on RGB images which provide rich texture information about the 3D scene. However, the quality of RGB images highly depends on environmental factors, which further influence the performance of deep learning models. Therefore, in this thesis, we aim to improve the performance and robustness of RGB models with comple…

Multi-Modal fusionApprentissage profond[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingDeep Learning for Computer VisionVision par ordinateurRGB-D FusionComputer visionDeep learningVision par Ordinateur et Intelligence Artificielle[INFO] Computer Science [cs]
researchProduct

3D shape recognition and matching for intelligent computer vision systems

2018

This thesis concerns recognition and matching of 3D shapes for intelligent computer vision systems. It describes two main contributions to this domain. The first contribution is an implementation of a new shape descriptor built on the basis of the spectral geometry of the Laplace-Beltrami operator; we propose an Advanced Global Point Signature (AGPS). This descriptor exploits the intrinsic structure of the object and organizes its information in an efficient way. In addition, AGPS is extremely compact since only a few eigenpairs were necessary to obtain an accurate shape description. The second contribution is an improvement of the wave kernel signature; we propose an optimized wave kernel …

Recherche par forme clef[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Reconnaissance de formesVision par ordinateurShape classificationShape matchingClassification de formes[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Computer visionShape recognition
researchProduct

Selection of optimal narrowband multispectral images for face recognition

2015

Face recognition systems based on ’conventional’ images have reached a significant level of maturity with some practical successes. However, their performance may degrade under poor and/or changing illumination. Multispectral imagery represents a viable alternative to conventional imaging in the search for a robust and practical identification system. Multi- spectral imaging (MI) can be defined as a ’collection of several monochrome images of the same scene, each of them taken with additional receptors sensitive to other frequencies of the visible light or to frequencies beyond the visible light like the infrared region of electro- magnetic continuum. Each image is referred to as a band or …

Reconnaissance de visage[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Visible spectrumVision par ordinateurMulti-spectral ImagesSpectre visibleComputer visionOptimisationImages multi-spectraleFace recognition
researchProduct

Contribution à l’apprentissage de représentation de données à base de graphes avec application à la catégorisation d’images

2020

Graph-based Manifold Learning algorithms are regarded as a powerful technique for feature extraction and dimensionality reduction in Pattern Recogniton, Computer Vision and Machine Learning fields. These algorithms utilize sample information contained in the item-item similarity and weighted matrix to reveal the intrinstic geometric structure of manifold. It exhibits the low dimensional structure in the high dimensional data. This motivates me to develop Graph-based Manifold Learning techniques on Pattern Recognition, specially, application to image categorization. The experimental datasets of thesis correspond to several categories of public image datasets such as face datasets, indoor and…

Représentation de données à base de graphesSemi supervised LearningReconnaissance de formesComputer Vision[INFO.INFO-OH]Computer Science [cs]/Other [cs.OH]Manifold LearningPattern Recognition[INFO.INFO-OH] Computer Science [cs]/Other [cs.OH]Machine LearningGraph based EmbeddingVision par ordinateurApprentissage de représentation de donnéesinformaticsApprentissage semi superviséinformáticaApprentissage machine
researchProduct

Optimisation et implémentation de méthodes bio-inspirées d'extraction de caractéristiques pour la reconnaissance d'objets visuels

2016

Industry has growing needs for so-called “intelligent systems”, capable of not only ac-quire data, but also to analyse it and to make decisions accordingly. Such systems areparticularly useful for video-surveillance, in which case alarms must be raised in case ofan intrusion. For cost saving and power consumption reasons, it is better to perform thatprocess as close to the sensor as possible. To address that issue, a promising approach isto use bio-inspired frameworks, which consist in applying computational biology modelsto industrial applications. The work carried out during that thesis consisted in select-ing bio-inspired feature extraction frameworks, and to optimize them with the aim t…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI][INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Bio-inspiréApprentissage automatiqueIntelligence artificielle[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Descripteurs[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]EmbarquéAlgorithm-architecture matching[ INFO.INFO-BI ] Computer Science [cs]/Bioinformatics [q-bio.QM]Vision par ordinateurMachine learningRéseaux de neuronesComputer vision[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM][ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI]OptimisationsFPGANeural networks[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM]
researchProduct

Tracking in Presence of Total Occlusion and Size Variation using Mean Shift and Kalman Filter

2011

International audience; The classical mean shift algorithm for tracking in perfectly arranged conditions constitutes a good object tracking method. However, in the real environment it presents some limitations, especially under the presence of noise, objects with varying size, or occlusions. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using mean shift and the Kalman filter, which was added to the traditional algorithm as a predictor when no reliable model of the object being tracked is found. Experimental work demonstrates that the proposed mean shift Kalman filter algorithm improves the tracking performance of the classical algorithms in c…

[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]OcclusionSize VariationTrackingVision par ordinateur et reconnaissance de formes [Informatique][INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Kalman FilterMean Shift Filter
researchProduct