articles+ search results

Computer science, Informatique, Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Telecommunications et theorie de l'information, Telecommunications and information theory, Théorie de l'information, du signal et des communications, Information, signal and communications theory, Théorie du signal et des communications, Signal and communications theory, Signal, bruit, Signal, noise, Détection, estimation, filtrage, égalisation, prédiction, Detection, estimation, filtering, equalization, prediction, Traitement du signal, Signal processing, Reconnaissance des formes, Pattern recognition, Traitement des images, Image processing, Traitement image, Image processing, Procesamiento imagen, Ajustement modèle, Model matching, Ajustamiento modelo, Complexité calcul, Computational complexity, Complejidad computación, Erreur quadratique moyenne, Mean square error, Error medio cuadrático, Estimation mouvement, Motion estimation, Estimación movimiento, Fibre monomode, Single mode fiber, Fibra monomoda, Forme tridimensionnelle, Three dimensional shape, Forma tridimensional, Image multiple, Multiple image, Imagen múltiple, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Mimique, Facial expression, Mímica, Modèle 3 dimensions, Three dimensional model, Modelo 3 dimensiones, Reconstitution forme, Pattern recovery, Reconstitución forma, Reconstruction de volume, Volume reconstruction, Reconstrucción volumétrica, Reconstruction image, Image reconstruction, Reconstrucción imagen, Scanneur, Scanner, Escáner, Séquence image, Image sequence, Secuencia imagen, Traitement signal, Signal processing, Procesamiento señal, Volume, Volumen, Vulnérabilité, Vulnerability, Vulnerabilidad, Technologie multi-vues, Multi-view technology, 3D facial reconstruction, 3D model fitting, Morphable model, Self-occlusion, Single view, and Structure from motion

The 3D Morphable Model (3DMM) and the Structure from Motion (SfM) methods are widely used for 3D facial reconstruction from 2D single-view or multiple-view images. However, model-based methods suffer from disadvantages such as high computational costs and vulnerability to local minima and head pose variations. The SfM-based methods require multiple facial images in various poses. To overcome these disadvantages, we propose a single-view-based 3D facial reconstruction method that is person-specific and robust to pose variations. Our proposed method combines the simplified 3DMM and the SfM methods. First, 2D initial frontal Facial Feature Points (FFPs) are estimated from a preliminary 3D facial image that is reconstructed by the simplified 3DMM. Second, a bilateral symmetric facial image and its corresponding FFPs are obtained from the original side-view image and corresponding FFPs by using the mirroring technique. Finally, a more accurate the 3D facial shape is reconstructed by the SfM using the frontal, original, and bilateral symmetric FFPs. We evaluated the proposed method using facial images in 35 different poses. The reconstructed facial images and the ground-truth 3D facial shapes obtained from the scanner were compared. The proposed method proved more robust to pose variations than 3DMM. The average 3D Root Mean Square Error (RMSE) between the reconstructed and ground-truth 3D faces was less than 2.6 mm when 2D FFPs were manually annotated, and less than 3.5 mm when automatically annotated.

Cognition, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Connexionnisme. Réseaux neuronaux, Connectionism. Neural networks, Algorithme Kohonen, Kohonen algorithm, Algoritmo Kohonen, Amas, Cluster, Montón, Autoorganisation, Self organization, Autoorganización, Carte graphique, Graphic processing unit, Unidad de proceso gráfico, Etude expérimentale, Experimental study, Estudio experimental, Fonction transfert, Transfer function, Función traspaso, Harmonique, Harmonic, Armónica, Harmonisation, Harmonization, Armonización, Image couleur, Color image, Imagen color, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Manipulation, Manipulación, Opacité, Opacity, Opacidad, Rendu image, Image rendering, Restitucíon imagen, Réseau neuronal, Neural network, Red neuronal, Résultat expérimental, Experimental result, Resultado experimental, Temps réel, Real time, Tiempo real, Topologie, Topology, Topología, Treillis, Lattice, Enrejado, Visualisation, Visualization, Visualización, Voxel, Conception centrée utilisateur, User centred design, Diseño centrado en el usuario, Color harmonization, Direct volume rendering, and Self-organizing map

Finding an appropriate transfer function (TF) for mapping color and opacity values in direct volume rendering (DVR) can be a daunting task. This paper presents a novel approach towards TF generation for DVR, where the traditional low-level color and opacity parameter manipulations are not necessary. The TF generation process is hidden behind a simple and intuitive spherical self-organizing map (SSOM) visualization. The SSOM represents a visual form of the topological relations among the clusters. The user interacts with the SSOM lattice to find interesting regions in the volume. The color and opacity values are generated automatically from the voxel features based on the user's perception. We also use harmonic colors to present a visually pleasing result. Due to the independence of SSOM from feature type, our proposed method is flexible in nature and can be integrated with any set of features. The GPU implementation provides real-time volume rendering and fast interaction. Experimental results on several benchmark volume datasets show the effectiveness of our proposed method.

Computer science, Informatique, Psychology, psychopathology, psychiatry, Psychologie, psychopathologie, psychiatrie, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Systèmes informatiques et systèmes répartis. Interface utilisateur, Computer systems and distributed systems. User interface, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Reconnaissance et synthèse de la parole et du son. Linguistique, Speech and sound recognition and synthesis. Linguistics, Agent intelligent, Intelligent agent, Agente inteligente, Analyse décision, Decision analysis, Análisis decisión, Animation par ordinateur, Computer animation, Animación por computador, Aveugle, Blind, Ciego, Calculateur processus, Process computer, Calculador proceso, Commerce électronique, Electronic trade, Comercio electronico, Discours, Discourse, Discurso, Durée, Duration, Duración, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Intelligence artificielle, Artificial intelligence, Inteligencia artificial, Interface graphique, Graphical interface, Interfaz grafica, Interface utilisateur, User interface, Interfase usuario, Langage artificiel, Artificial language, Lenguaje artificial, Langage naturel, Natural language, Lenguaje natural, Linguistique, Linguistics, Linguística, Prise de décision, Decision making, Toma decision, Représentation graphique, Graphics, Grafo (curva), Robot, Réalité virtuelle, Virtual reality, Realidad virtual, Vêtement, Clothing, Vestidura, Indistinguabilité, Indistinguishability, Indistinguibilidade, Langage marquage, Markup language, Lenguaje marcación, Avatars, Human-computer interaction, Second Life, Turing Test, and Virtual worlds

The current study involved the first natural language, modified Turing Test in a 3D virtual environment. One hundred participants were given an avatar-guided tour of a virtual clothing store housed in the 3D world of Second Life. In half of the cases, a human research assistant controlled the avatar-guide; in the other half, the avatar-guide was a visually indistinguishable virtual agent or bot that employed a chat engine called Discourse, a more robust variant of Artificial Intelligence Markup Language (AIML). Both participants and the human research assistant were blind to variations in the controlling agency of the guide. The results indicated that 78% of participants in the artificial intelligence condition incorrectly judged the bot to be human, significantly exceeding the 50% rate that one would expect by chance alone that is used as the criterion for passage of a modified Turing Test. An analysis of participants' decision-making criteria revealed that agency judgments were impacted by both the quality of the AI engine and a number of psychological and contextual factors, including the naivety of participants regarding the possible presence of an intelligent agent, the duration of the trial period, the specificity and structure of the test situation, and the anthropomorphic form and movements of the agent. Thus, passage of the Turing Test is best viewed not as the sole product of advances in artificial intelligence or the operation of psychological and contextual variables, but as a complex process of human-computer interaction.

Computer science, Informatique, Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Telecommunications et theorie de l'information, Telecommunications and information theory, Théorie de l'information, du signal et des communications, Information, signal and communications theory, Théorie du signal et des communications, Signal and communications theory, Signal, bruit, Signal, noise, Représentation du signal. Analyse spectrale, Signal representation. Spectral analysis, Détection, estimation, filtrage, égalisation, prédiction, Detection, estimation, filtering, equalization, prediction, Traitement du signal, Signal processing, Traitement des images, Image processing, Algorithme apprentissage, Learning algorithm, Algoritmo aprendizaje, Analyse mouvement, Motion analysis, Análisis movimiento, Apprentissage, Learning, Aprendizaje, Classification automatique, Automatic classification, Clasificación automática, Classification signal, Signal classification, Etat actuel, State of the art, Estado actual, Evaluation performance, Performance evaluation, Evaluación prestación, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Machine vecteur support, Support vector machine, Máquina vector soporte, Modélisation, Modeling, Modelización, Méthode vectorielle, Vector method, Método vectorial, Observabilité, Observability, Observabilidad, Processus Gauss, Gaussian process, Proceso Gauss, Squelette, Skeleton, Esqueleto, Système dynamique, Dynamical system, Sistema dinámico, Traitement signal, Signal processing, Procesamiento señal, Classification, Depth images, Grassmann manifold, Human action recognition, and Observational latency

In this paper we address the problem of modeling and analyzing human motion by focusing on 3D body skeletons. Particularly, our intent is to represent skeletal motion in a geometric and efficient way, leading to an accurate action-recognition system. Here an action is represented by a dynamical system whose observability matrix is characterized as an element of a Grassmann manifold. To formulate our learning algorithm, we propose two distinct ideas: (1) in the first one we perform classification using a Truncated Wrapped Gaussian model, one for each class in its own tangent space. (2) In the second one we propose a novel learning algorithm that uses a vector representation formed by concatenating local coordinates in tangent spaces associated with different classes and training a linear SVM. We evaluate our approaches on three public 3D action datasets: MSR-action 3D, UT-kinect and UCF-kinect datasets; these datasets represent different kinds of challenges and together help provide an exhaustive evaluation. The results show that our approaches either match or exceed state-of-the-art performance reaching 91.21% on MSR-action 3D, 97.91% on UCF-kinect, and 88.5% on UT-kinect. Finally, we evaluate the latency, i.e. the ability to recognize an action before its termination, of our approach and demonstrate improvements relative to other published approaches.

Cardiology, blood circulation, phlebology, Cardiologie, appareil circulatoire, phlébologie, Sciences biologiques et medicales, Biological and medical sciences, Sciences medicales, Medical sciences, Cardiologie. Appareil circulatoire, Cardiology. Vascular system, Vaisseaux sanguins et lymphatiques, Blood and lymphatic vessels, Maladies vasculaires des membres. Pathologie de la veine cave. Maladies vasculaires diverses, Diseases of the peripheral vessels. Diseases of the vena cava. Miscellaneous, Pathologie des vaisseaux sanguins, Vascular disease, Vaso sanguíneo patología, Vaisseau sanguin, Blood vessel, Vaso sanguíneo, Anatomie, Anatomy, Anatomía, Appareil circulatoire, Circulatory system, Aparato circulatorio, Compression, Compresión, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Interface, Interfase, Jambe, Leg, Pierna, Membre inférieur, Lower limb, Miembro inferior, Mesure pression, Pressure measurement, Medida presión, Modèle, Models, Modelo, Médecine, Medicine, Medicina, Pathologie de l'appareil circulatoire, Cardiovascular disease, Aparato circulatorio patología, Pathologie des veines, Venous disease, Vena patología, Pression, Pressure, Presión, Traitement image, Image processing, Procesamiento imagen, Veine, Vein, Vena, anatomie veineuse de la jambe, compression médicale, modèle 3D, pression d'interface, and pression intramusculaire

Contexte: À partir d'une étude anatomique avec modélisation tridimensionnelle des veines de jambe par IRM en position debout, nous avons montré récemment qu'une compression médicale exerçant une pression d'interface (PI) de 22 mmHg, réduit significativement le calibre des veines profondes, mais paradoxalement n'a que peu d'effet sur les veines superficielles en orthostatisme. Objectifs: Expliciter ce paradoxe de la compression, c'est-à-dire montrer que le calibre des veines profondes de jambe, en position debout, peut être diminué par des pressions inférieures à celles de veines superficielles. Tenter d'expliquer ce paradoxe par l'étude de la corrélation entre la PI exercée par la compression et la pression intramusculaire (PIM) du mollet. Matériel et méthodes: 1. Une étude utilisant l'IRM debout a été réalisée chez 12 sujets (dont 4 sujets porteurs de varices). À partir des coupes réalisées en T2 sur une hauteur de 15 cm sur partie haute du mollet, nous avons utilisé le logiciel Winsurf® pour faire une modélisation 3D des éléments anatomiques de la jambe, en particulier chaque groupe de veines ainsi que les compartiments musculaires. Ceci a permis de mesurer leurs variations de volume en fonction de la position et de la PI exercée par la compression. 2. Utilisant 10 jambes de 5 sujets sains, nous avons étudié les effets engendrés par différentes pressions d'interface sur la PIM du muscle gastrocnémien médiat. La pression d'interface était produite par un brassard à tension et contrôlée par un système Picopress® placé sous le brassard. La pression intramusculaire a été mesurée avec une aiguille 21G connectée à un manomètre. Les PIM ont été enregistrées en position couchée et debout immobile en augmentant la pression du brassard de 0 à 50 mmHg tous les 10 mmHg. Résultats: Étude 1: Avec une PI de 22 mmHg en position debout, on observe une réduction de calibre très significative des veines profondes (surtout des veines fibulaires et soléaires) mais pas de changement des veines superficielles. Pour comprimer ces dernières, il faut une pression supérieure d'environ 60 mmHg. Étude 2: En position couchée au repos, une pression d'interface de moins de 20 mmHg ne modifie pas significativement la pression intramusculaire. Au contraire, une parfaite corrélation linéaire (r = 0,99) est observée avec des pressions croissantes de 20 à 50 mmHg. Des résultats identiques sont retrouvés en position debout. Conclusion: Cette étude a montré qu'en position debout, une pression d'interface de 22 mmHg provoque une augmentation significative de la pression intramusculaire du jumeau médial de 32 à 54 mmHg. Pendant le même temps, chez ces sujets sains, la pression sous-cutanée reste proche de celle du brassard, soit 22 mmHg. Cette dernière pression est insuffisante pour comprimer les veines superficielles en position debout, alors qu'à 54 mmHg on observe une nette réduction de calibre des veines profondes. Ceci est en accord avec le paradoxe de la compression retrouvé dans notre première étude.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Informatique théorique, Theoretical computing, Algorithmique. Calculabilité. Arithmétique ordinateur, Algorithmics. Computability. Computer arithmetics, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Angle observation, Viewing angle, Angulo observación, Automatisation, Automation, Automatización, Boîte, Box, Caja, Classe complexité, Complexity class, Clase complejidad, Echantillonnage, Sampling, Muestreo, Efficacité, Efficiency, Eficacia, Géométrie algorithmique, Computational geometry, Geometría computacional, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Modélisation, Modeling, Modelización, Numérisation, Digitizing, Numerización, Planification, Planning, Planificación, Processus acquisition, Acquisition process, Proceso adquisición, Robustesse, Robustness, Robustez, Système intelligent, Intelligent system, Sistema inteligente, Tracé rayon, Ray tracing, Trazado rayos, Visibilité, Visibility, Visibilidad, Vision ordinateur, Computer vision, Visión ordenador, 3D digitization, automation, non model-based method, and view planning

This paper presents three methods for the digitization of 3D objects without prior knowledge on their shape. The first method is simple and naïve and is based on the generation of view points by sampling the bounding box of the acquired data at each step of the acquisition process. The second method is an analysis of the orientation of the scanned parts. The third method explores the barely visible surfaces and is a combination of the angular visibility and the real one by ray tracing. Tests with objects of different complexity classes were performed. The results of digitization are provided and prove the efficiency and the robustness of our approaches.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Albédo, Albedo, Ambiguité, Ambiguity, Ambiguedad, Eclairage, Lighting, Alumbrado, Efficacité, Efficiency, Eficacia, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Infographie, Computer graphics, Gráfico computadora, Observation aberrante, Outlier, Observación aberrante, Ombre, Shadow, Sombra, Photométrie, Photometry, Fotometría, Reconstruction image, Image reconstruction, Reconstrucción imagen, Relief, Relieve, Sculpture, Escultura, Source lumineuse, Light source, Fuente luminosa, Source lumière, Light sources, Traitement image, Image processing, Procesamiento imagen, Vision ordinateur, Computer vision, Visión ordenador, Vision stéréoscopique, Stereopsis, Visión estereoscópica, 3D-reconstruction, generalized bas-relief ambiguity, lighting estimation, shadows, shape-from-X, specular highlights, and uncalibrated photometric stereo

In this paper we present a robust method for solving the uncalibrated photometric stereo problem in the Lambertian framework, in presence of outliers such as shadows or specular highlights. We show how to detect such outliers so as to accurately estimate the light sources, which are assumed to have uniform magnitude in order to solve for the generalized bas-relief ambiguity. We then propose a way to recover both the normal and the albedo in every pixel in presence of outliers, which is made possible thanks to the accurate estimation of the light sources. Our method is validated both qualitatively and quantitatively on synthetic and real-world datasets, and we compare its efficiency and accuracy to the most state-of-the-art existing techniques.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Organisation des mémoires. Traitement des données, Memory organisation. Data processing, Traitement des données. Listes et chaînes de caractères, Data processing. List processing. Character string processing, Apprentissage supervisé, Supervised learning, Aprendizaje supervisado, Classification, Clasificación, Faciès, Facies, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Modèle agrégé, Aggregate model, Modelo agregado, Perspective, Perspectiva, Photographie panoramique, Panoramic photography, Fotografía panorámica, Représentation spatiale, Spatial representation, Representación espacial, Transformation géométrique, Geometric transformation, Transformación geométrica, Vision omnidirectionnelle, Omnidirectional vision, Visión omnidireccional, Vision ordinateur, Computer vision, Visión ordenador, Détection objet, Object detection, Detección de Objetos, Reconnaissance visage, Face recognition, Reconocimiento de cara, boosting, face detection, and omnidirectional vision

Omnidirectional vision sensors are mainly used for geometrical interpretation of scenes. However, few researchers have investigated how to perform object detection with such systems. The existing approaches require a geometrical transformation prior to the interpretation of the omnidirectional images. The face detection algorithm trained on perspective images is then applied on the unwrapped image. In this paper, we focus on how to process the omnidirectional images as provided by the sensor. While adapting algorithms developed for perspective images to omnidirectional images, our results suggest that the choice of descriptors is a critical step.

Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Systèmes informatiques et systèmes répartis. Interface utilisateur, Computer systems and distributed systems. User interface, Organisation des mémoires. Traitement des données, Memory organisation. Data processing, Systèmes d'information. Bases de données, Information systems. Data bases, Conception assistée, Computer aided design, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Amas, Cluster, Montón, Aspect dynamique, Dynamic aspect, Aspecto dinámico, Base de données répartie, Distributed database, Base repartida dato, Calcul réparti, Distributed computing, Cálculo repartido, Centre calcul, Computer center, Centro cálculo, Centre donnée, Data center, Centro datos, Cognition, Cognición, Esthétique, Aesthetics, Estética, Flux donnée, Data flow, Flujo datos, Haute performance, High performance, Alto rendimiento, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Recherche multibase, Multidatabase retrieval, Búsqueda multibase, Représentation système, System representation, Representación sistema, Réplication, Replication, Replicación, Système grande taille, Large scale system, Sistema gran escala, Système information, Information system, Sistema información, Sémantique, Semantics, Semántica, Théorie cognitive, Cognitive theory, Teoría cognitiva, Traitement flux donnée, Data flow processing, Base donnée très grande, Very large databases, Base de datos a gran escala, Modèle donnée, Data models, Modelo de datos, Visualisation donnée, Data visualization, Visualización de datos, big data flow, cognitive/perceptual processing of large and dynamic data sets, data design, data visualization, and graphical (re)presentation of data

To cope with the information deluge due to an exponentially increasing amount of data (created and replicated digitally), it is essential to design large-scale visual information systems offering pragmatic and semantic modes of representation for huge data flows (and clusters) as well as efficient tools for visualizing data set volumetric variations and fluctuations. Breaking away from standard design methods and data presentation-centered models (data visualizations and infographics), new data design approaches build currently mixed contextual and environmental representation-visualization systems that enable people to visualize (at different scales) and understand the dynamic aspects of part-whole relationships between multiple databases. In this paper, we will define a new conceptual framework for cognitive-aesthetic analysis of these original big data flow representation-visualization models.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Angle observation, Viewing angle, Angulo observación, Art, Arte, Coloration, Coloración, Colorimétrie, Colorimetry, Colorimetría, Documentation, Documentación, Haute résolution, High resolution, Alta resolucion, Histoire, History, Historia, Image numérique, Digital image, Imagen numérica, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Laser, Láser, Monument, Monumento, Métrologie surface, Surface metrology, Metrología superficie, Numérisation, Digitizing, Numerización, Optimisation, Optimization, Optimización, Patrimoine bâti, Building stock, Patrimonio construido, Photométrie, Photometry, Fotometría, Polygone, Polygon, Polígono, Recalage image, Image registration, Registro imagen, Traitement image, Image processing, Procesamiento imagen, Visualisation, Visualization, Visualización, Nuage points, Point cloud, Nube de puntos, colorization, point clouds, and visual and virtual optimization

Architectural heritage is a historic and artistic property which has to be protected, preserved, restored and must be shown to the public. Modern tools like 3D laser scanners are more and more used in heritage documentation. These systems allow fast generation of accurate point clouds of historical monuments. Using these data, we are able to create a polygon mesh that defines the shape of the edifice for virtual visualization. Most of the time, the 3D laser scanner is completed by a digital camera which is usedto colorize the point cloud. However, the photometric quality of point clouds is generally ratherlow, mainly due to color and resolution problems. Intensity uniformization methods exist to improve the colorimetry but they do not permit to obtain a photo-realist rendering nor to globally improve the resolution. That is why this paper proposes a solution to colorize point clouds using high resolution digital images acquired with a camera from any viewpoint. For this, we have developed a new accurate method for registering the photographs on the point cloud which is a crucial step for a good colorization by color projection. Results, on datasets of the cathedral of Amiens in France, highlight the success of our approach, leading to point clouds with better photometric quality and resolution.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Sciences biologiques et medicales, Biological and medical sciences, Sciences medicales, Medical sciences, Techniques d'exploration et de diagnostic (generalites), Investigative techniques, diagnostic techniques (general aspects), Exploration radioisotopique, Radionuclide investigations, Calcul variationnel, Variational calculus, Cálculo de variaciones, Champ force, Force field, Campo fuerza, Déformation mécanique, Mechanical deformation, Deformación mecánica, Identification aveugle, Blind identification, Identificación ciega, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Modélisation, Modeling, Modelización, Méthode Monte Carlo, Monte Carlo method, Método Monte Carlo, Scintigraphie, Scintigraphy, Centelleografía, Tomographie par émission de positons, Positron emission tomography, Tomografía emisión positrones, Tomoscintigraphie positon, Positron computed tomography, Traitement image, Image processing, Procesamiento imagen, Segmentation image, Image segmentation, Segmentación de imágenes, Tenseur de structure, Structure tensor, Tensor de estructura, 3D segmentation, deformable models, and dynamic PET

In this paper, we generalize the gradient vector flow field to vector-valued images. We base our method on the definition of a structure tensor that is calculated according to a blind estimation of contrast in the different channels and that exploits the whole spatiospectral information, hence reducing sensitivity to noise and better defining orientations of the force field. The resulting field takes profit of both magnitude and direction of the vector-valued gradient. Applied to biological volume delineation in 3D dynamic Positron Emission Tomography (PET) imaging, we validate our method on realistic Monte Carlo simulations of numerical phantoms and present results on real dynamic PET data. Performances observed on such images confirm the potential of the proposed active surface approach for vector-valued data.

Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Generalites, General aspects, Formation professionnelle. Personnel. Organisation du travail, Occupational training. Personnel. Work management, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Systèmes informatiques et systèmes répartis. Interface utilisateur, Computer systems and distributed systems. User interface, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Image numérique, Digital image, Imagen numérica, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Modélisation, Modeling, Modelización, Prise vue, Photographing, Toma vista, Recommandation, Recommendation, Recomendación, Reconstruction image, Image reconstruction, Reconstrucción imagen, Robustesse, Robustness, Robustez, Réseau social, Social network, Red social, Résultat expérimental, Experimental result, Resultado experimental, Source information, Information source, Fuente información, Système coordonnée, Coordinate system, Sistema coordenadas, Temps réel, Real time, Tiempo real, Traitement image, Image processing, Procesamiento imagen, Téléenseignement, Remote teaching, Teleensenanza, Téléphone portable, Mobile phone, Teléfono móvil, Vision ordinateur, Computer vision, Visión ordenador, Appariement image, Image matching, reconocimiento de patrones en imágenes, 3D model reconstruction, Knowledge learning, Landmark recognition, and Photographing recommendation

In this paper, we study the problem of human position recommendation in mobile photographing and propose a learning-based method to summarize the photographing knowledge from massive social images to improve the robustness and effectiveness. In contrast to existing photographing guide methods, we focus on turning to the collaborative web data source and learning the distribution of human position. To overcome the challenges in landmark image alignment and the relative human position projection, we propose a 3D reconstruction-based method to align the background region and human region into a uniform coordinate system. Finally, a camera-view sensitive human position recommendation strategy is carried out. A dataset containing 30,000 photos of ten landmark scenes is collected from Flickr, and a group of experiments are conducted comparing both our alternatives and various other baseline methods. Moreover, an application is developed on mobile phones to implement the real-time photographing recommendation. The experimental results show that our proposed framework achieves promising results, which demonstrate the robustness and effectiveness of our approach.

Documentation, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Systèmes informatiques et systèmes répartis. Interface utilisateur, Computer systems and distributed systems. User interface, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Gestion contenu, Content management, Gestión contenido, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Internet, Modélisation, Modeling, Modelización, Navigation information, Information browsing, Navegacíon informacíon, Réalité virtuelle, Virtual reality, Realidad virtual, Réseau web, World wide web, Red WWW, Temps réel, Real time, Tiempo real, Format fichier, File format, Formato fichero, Blender, Canvas, HTML5, VR 3D web, VR contents, and X3D

Virtual reality 3D web technology can combine with HTML5 technologies and X3D contents to achieve real-time display without plug-in. X3D strives to become the 3D standard for the web as integrated in the HTML5 standard. HTML5 is able to support X3D format to achieve 3D virtual reality on the web. Blender software can create 3D models and export them to X3D files. X3D files are displayed in real time on web browsers that support HTML5. The X3D files created with Blender software give users excellent 3D real-time interactive operation experience. Therefore this paper introduces how to achieve 3D virtual reality contents on the web by using X3D files and HTML5 canvas.

Biomedical engineering, Génie biomédical, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Informatique théorique, Theoretical computing, Recherche information. Graphe, Information retrieval. Graph, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Sciences biologiques et medicales, Biological and medical sciences, Sciences medicales, Medical sciences, Techniques d'exploration et de diagnostic (generalites), Investigative techniques, diagnostic techniques (general aspects), Exploration radioisotopique, Radionuclide investigations, Système ostéoarticulaire. Muscles, Osteoarticular system. Muscles, Approche probabiliste, Probabilistic approach, Enfoque probabilista, Coupe graphe, Graph cut, Corte grafo, Densité minérale osseuse, Bone mineral density, Masa mineral ósea, Défaut forme, Form defect, Defecto forma, Fonction énergie, Energy function, Función energía, Forme géométrique, Geometrical shape, Forma geométrica, Image niveau gris, Grey level image, Imagen nivel gris, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Interpolation linéaire, Linear interpolation, Interpolación lineal, Loi Poisson, Poisson distribution, Ley Poisson, Modélisation, Modeling, Modelización, Processus Gauss, Gaussian process, Proceso Gauss, Radiographie RX, X ray radiography, Radiografía RX, Résultat expérimental, Experimental result, Resultado experimental, Théorie graphe, Graph theory, Teoría grafo, Variabilité, Variability, Variabilidad, Voxel, Classification image, Image classification, Clasificación de imágenes, Segmentation image, Image segmentation, Segmentación de imágenes, BMD, GC, Segmentation, Shape, and VB

We propose a novel vertebral body segmentation approach, which is based on the graph cuts technique with shape constraints. The proposed approach depends on both image appearance and shape information. Shape information is gathered from a set of training shapes. Then we estimate the shape variations using a new distance probabilistic model which approximates the marginal densities of the vertebral body and its background in the variability region using a Poisson distribution refined by positive and negative Gaussian components. To segment a vertebral body, we align its 3D shape with the training 3D shape so we can use the distance probabilistic model. Then its gray level is approximated with a Linear Combination of Gaussians (LCG) with sign-alternate components. The spatial interaction between the neighboring voxels is identified using a new analytical approach. Finally, we formulate an energy function using both appearance models and shape constraints. This function is globally minimized using s/t graph cuts to get the optimal segmentation. Experimental results show that the proposed technique gives promising results compared to other alternatives. Applications on Bone Mineral Density (BMD) measurements of vertebral body are given to illustrate the accuracy of the proposed segmentation approach.

Control theory, operational research, Automatique, recherche opérationnelle, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Brillance, Brightness, Brillantez, Eclairement, Illumination, Alumbrado, En ligne, On line, En línea, Etalonnage, Calibration, Contraste, Faciès, Facies, Formation image, Imaging, Formación imagen, Hors ligne, Off line, Fuera linea, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Luminance, Luminancia, Méthode indirecte, Indirect method, Método indirecto, Méthodologie, Methodology, Metodología, Photométrie, Photometry, Fotometría, Reconstruction image, Image reconstruction, Reconstrucción imagen, Traitement image, Image processing, Procesamiento imagen, Vision ordinateur, Computer vision, Visión ordenador, Vision stéréoscopique, Stereopsis, Visión estereoscópica, Reconnaissance visage, Face recognition, Reconocimiento de cara, 3D face reconstruction, Flatfielding, Illumination vector estimation, Inverse-square law for light propagation, and Photometric stereo

Within the context of photometric stereo reconstruction, flatfielding may be used to compensate for the effect of the inverse-square law of light propagation on the pixel brightness. This would require capturing a set of reference images at an off-line imaging session, which employs a calibrating device that should be captured under the exact conditions as the main session. Similarly, the illumination vectors, on which photometric stereo relies, are typically pre-computed based on another dedicated calibration session. In practice, implementing such off-line sessions is inconvenient and often infeasible. This work aims at enabling accurate photometric stereo reconstruction for the case of non-interactive on-line capturing of human faces. We propose unsupervised methodologies, which extract all information that is required for accurate face reconstruction from the images of interest themselves. Specifically, we propose an uncalibrated flatfielding and an uncalibrated illumination vector estimation methodology, and we assess their effect on photometric stereo face reconstruction. Results demonstrate that incorporating our methodologies into the photometric stereo framework halves the reconstruction error, while eliminating the need of off-line calibration.

Mechanical engineering, Génie mécanique, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Conception assistée, Computer aided design, Analyse conceptuelle, Conceptual analysis, Análisis conceptual, Analyse fonctionnelle, Functional analysis, Análisis funcional, Analyse structurale, Structural analysis, Análisis estructural, Conception assistée, Computer aided design, Concepción asistida, Conception ingénierie, Engineering design, Concepción ingeniería, Conception intégrée, Integrated design, Concepción integrada, Cycle développement, Life cycle, Ciclo desarrollo, Développement durable, Sustainable development, Desarrollo sostenible, Développement produit, Product development, Desarrollo producto, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Impact environnement, Environment impact, Impacto medio ambiente, Modélisation, Modeling, Modelización, Optimisation, Optimization, Optimización, Paramètre géométrique, Geometrical parameter, Parámetro geométrico, Processus fabrication, Production process, Proceso fabricación, Réalité virtuelle, Virtual reality, Realidad virtual, Système aide décision, Decision support system, Sistema ayuda decisíon, CAE, Eco-design, LCA, and Structural optimization

This paper addresses the need for a structured approach to environmental assessment and improvement. We propose a computer-aided methodology, named Eco-OptiCAD, based on the integration of Structural Optimization and Life Cycle Assessment (LCA) tools. Eco-OptiCAD supports the designer during product development, highlighting when and where the core of the environmental impact lies. Furthermore, it provides effective tools to address such impacts, improving the original product, while ensuring structural and functional requirements. It foresees the synergic use of (1) virtual prototyping tools, such as 3D CAD, Finite Element Analysis (FEA) and Structural optimization, (2) function modeling methodology and (3) Life Cycle Assessment (LCA) tools. The kernel of the methodology is constituted by a set of optimization strategies and a module, named Life Cycle Mapping (LCM). In particular, we have conceived ten optimization strategies converting environmental objectives and constraints into structural and geometrical parameters. They enable the designer to generate alternative green scenarios according to the triad shape―material―production. The LCM tool has been specifically developed to easily trace the growth of environmental impacts throughout the product's life cycle and allow the user to focus his effort on the most relevant aspects. Thanks to the integration of the structural optimizer with an LCA map, the designer becomes aware of the consequences that each change in the geometry, the material or the manufacturing process will produce on the environmental impact of the product throughout its life cycle. With a complete view of the product life cycle, the designer can improve a single phase, while retaining a global perspective; thus avoiding the possibility of gaining a local green improvement at the cost of a global increase in environmental impacts. An exemplary case study is presented to detail each step of the design methodology and shows its potential. Eco-OptiCAD represents a first step toward a fully integrated system for eco-design assessment and improvement, with the potential of working side by side with common design tools, in providing a constant environmental feedback.

Telecommunications, Télécommunications, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Telecommunications et theorie de l'information, Telecommunications and information theory, Télécommunications, Telecommunications, Radiorepérage et radionavigation, Radiolocalization and radionavigation, Capteur mesure, Measurement sensor, Captador medida, Champ proche, Near field, Campo próximo, Conception système, System design, Concepción sistema, Evaluation performance, Performance evaluation, Evaluación prestación, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Imagerie onde millimétrique, Millimeter wave imaging, Imageur, Imager, Modèle 3 dimensions, Three dimensional model, Modelo 3 dimensiones, Onde millimétrique, Millimetric wave, Onda milimétrica, Optimisation, Optimization, Optimización, Problème inverse, Inverse problem, Problema inverso, Radar, Recuit simulé, Simulated annealing, Recocido simulado, Réseau lacunaire, Sparse array, Antena esparcida, Simulation, Simulación, Sécurité, Safety, Seguridad, Echantillonnage parcimonieux, Compressed sensing, imaging systems, inverse methods, millimeter wave radar, and sparse arrays

The optimization and use of a sparse array configuration for an active three dimensional (3D) millimeter wave imaging system for personnel security screening is presented in this work. The combination of the optimization procedure with the use of Compressed Sensing techniques allows drastic reduction in the number of sensors, thereby simplifying the system design and fabrication and reducing its cost. Representative simulation results showing good performance of the proposed system are provided and supported by sample measurements.

Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Logiciel, Software, Systèmes informatiques et systèmes répartis. Interface utilisateur, Computer systems and distributed systems. User interface, Affichage, Display, Visualización, Ajustement modèle, Model matching, Ajustamiento modelo, Angle observation, Viewing angle, Angulo observación, Artefact, Artefacto, Contrôle qualité, Quality control, Control de calidad, Disparité, Disparity, Disparidad, Evaluation subjective, Subjective evaluation, Evaluación subjetiva, Filtre passe bas, Low pass filter, Filtro paso bajo, Gestion contenu, Content management, Gestión contenido, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Profondeur champ, Depth of field, Profundidad campo, Reconstruction image, Image reconstruction, Reconstrucción imagen, Signal vidéo, Video signal, Señal video, Stéréoscopie, Stereoscopy, Estereoscopia, Verre, Glass, Vidrio, Vision stéréoscopique, Stereopsis, Visión estereoscópica, Effet fantôme, Ghosting artefact, Efecto fantasma, 2DV, 3DV, Contrast adjustment, Depth perception, Disparity adjustment, Low pass filtering, Stereoscopic, and Subjective quality assessment

Viewing stereoscopic 3D content is typically enabled either by using polarizing or active shutter glasses. In certain cases, some viewers may not wear viewing glasses and hence, it would be desirable to tune the stereoscopic 3D content so that it could be simultaneously watched with and without viewing glasses. In this paper we propose a video post-processing technique which enables good quality 3D and 2D perception of the same content. This is done through manipulation of one view by making it more similar to the other view to reduce the ghosting artifact perceived without viewing glasses while 3D perception is maintained. The proposed technique includes three steps: disparity selection, contrast adjustment, and low-pass filtering. The proposed approach was evaluated through an extensive series of subjective tests, which also revealed good adjustment parameters to suit viewing with and without viewing glasses with an acceptable 3D and 2D quality, respectively.

Cognition, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Analyse Fourier, Fourier analysis, Análisis Fourier, Analyse image, Image analysis, Análisis imagen, Artefact, Artefacto, Automobile, Motor car, Automóvil, Contenu image, Image content, Contenido imagen, Coordonnée polaire, Polar coordinate, Coordenada polar, Coordonnée sphérique, Spherical coordinate, Coordenada esférica, Discrétisation, Discretization, Discretización, Harmonique sphérique, Spherical harmonic, Armónica esférica, Haute performance, High performance, Alto rendimiento, Histogramme, Histogram, Histograma, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Invariance, Invarianza, Photographie aérienne, Aerial photography, Fotografía aérea, Représentation irréductible, Irreducible representation, Representación irreductible, Signal continu, Continuous signal, Señal continua, Similitude, Similarity, Similitud, Surveillance, Vigilancia, Vision ordinateur, Computer vision, Visión ordenador, Détection objet, Object detection, Detección de Objetos, Feature design, Histogram of oriented gradients, Image descriptor, Rotation-invariance, Spherical harmonics, and Volumetric data

The histogram of oriented gradients (HOG) is widely used for image description and proves to be very effective. In many vision problems, rotation-invariant analysis is necessary or preferred. Popular solutions are mainly based on pose normalization or learning, neglecting some intrinsic properties of rotations. This paper presents a method to build rotation-invariant HOG descriptors using Fourier analysis in polar/spherical coordinates, which are closely related to the irreducible representation of the 2D/3D rotation groups. This is achieved by considering a gradient histogram as a continuous angular signal which can be well represented by the Fourier basis (2D) or spherical harmonics (3D). As rotation-invariance is established in an analytical way, we can avoid discretization artifacts and create a continuous mapping from the image to the feature space. In the experiments, we first show that our method outperforms the state-of-the-art in a public dataset for a car detection task in aerial images. We further use the Princeton Shape Benchmark and the SHREC 2009 Generic Shape Benchmark to demonstrate the high performance of our method for similarity measures of 3D shapes. Finally, we show an application on microscopic volumetric data.

Cognition, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Reconnaissance des formes. Traitement numérique des images. Géométrie algorithmique, Pattern recognition. Digital image processing. Computational geometry, Analyse scène, Scene analysis, Análisis escena, Angle observation, Viewing angle, Angulo observación, Cartographie, Cartography, Cartografía, Comportement utilisateur, User behavior, Comportamiento usuario, Echelle grande, Large scale, Escala grande, Géométrie constructive, Constructive geometry, Geometría constructiva, Géométrie solide, Solid geometry, Geometría sólidos, Image tridimensionnelle, Tridimensional image, Imagen tridimensional, Installation intérieure, Indoor installation, Instalación interior, Laser, Láser, Localisation, Localization, Localización, Modélisation, Modeling, Modelización, Musée, Museum, Museo, Navigation, Navegación, Reconstruction image, Image reconstruction, Reconstrucción imagen, Rendu image, Image rendering, Restitucíon imagen, Texture, Textura, Traitement image, Image processing, Procesamiento imagen, Vision ordinateur, Computer vision, Visión ordenador, Zoom, Image réaliste, Realistic images, Imágen realista, Visualisation donnée, Data visualization, Visualización de datos, 3D reconstruction, Large-scale image-based modeling, and Photorealistic indoor maps

Virtual exploration tools for large indoor environments (e.g. museums) have so far been limited to either blueprint-style 2D maps that lack photo-realistic views of scenes, or ground-level image-to-image transitions, which are immersive but ill-suited for navigation. On the other hand, photorealistic aerial maps would be a useful navigational guide for large indoor environments, but it is impossible to directly acquire photographs covering a large indoor environment from aerial viewpoints. This paper presents a 3D reconstruction and visualization system for automatically producing clean and well-regularized texture-mapped 3D models for large indoor scenes, from ground-level photographs and 3D laser points. The key component is a new algorithm called inverse constructive solid geometry (CSG) for reconstructing a scene with a CSG representation consisting of volumetric primitives, which imposes powerful regularization constraints. We also propose several novel techniques to adjust the 3D model to make it suitable for rendering the 3D maps from aerial viewpoints. The visualization system enables users to easily browse a large-scale indoor environment from a bird's-eye view, locate specific room interiors, fly into a place of interest, view immersive ground-level panorama views, and zoom out again, all with seamless 3D transitions. We demonstrate our system on various museums, including the Metropolitan Museum of Art in New York City—one of the largest art galleries in the world.