Search results for "Signal"
showing 10 items of 6924 documents
Nouvelles méthodes de traitement de signaux multidimensionnels par décomposition suivant le théorème de Superposition de Kolmogorov
2010
The processing of multidimensional signal remains difficult when using monodimensional-based methods. Therefore, it is either required to extend monodimensional methods to several dimensions, which is not always possible, or to convert the multidimensional signals into 1D signals. In this case, the priority is to preserve most of the properties of the original signal. In this context, the Kolmogorov Superposition Theorem offers a promising theoretical framework for multidimensional signal conversion. In 1957, Kolmogorov demonstrated that any multivariate function can be written as sums and compositions of monovariate functions.We have focused on the image decomposition according to the supe…
Towards visual urban scene understanding for autonomous vehicle path tracking using GPS positioning data.
2019
This PhD thesis focuses on developing a path tracking approach based on visual perception and localization in urban environments. The proposed approach comprises two systems. The first one concerns environment perception. This task is carried out using deep learning techniques to automatically extract 2D visual features and use them to learn in order to distinguish the different objects in the driving scenarios. Three deep learning techniques are adopted: semantic segmentation to assign each image pixel to a class, instance segmentation to identify separated instances of the same class and, image classification to further recognize the specific labels of the instances. Here our system segme…
On Keyframe Positioning for Pose Graphs Applied to Visual SLAM
2013
International audience; In this work, a new method is introduced for localization and keyframe identification to solve a Simultaneous Localization and Mapping (SLAM) problem. The proposed approach is based on a dense spherical acquisition system that synthesizes spherical intensity and depth images at arbitrary locations. The images are related by a graph of 6 degrees-of-freedom (DOF) poses which are estimated through spherical registration. A direct image-based method is provided to estimate pose by using both depth and color information simultaneously. A new keyframe identification method is proposed to build the map of the environment by using the covariance matrix between raletive 6 DOF…
Performance evaluation of Wireless Sensor Networks based on ZigBee technology in smart home
2013
International audience; Wireless Sensor Networks (WSNs) has diverse application domains such as smart home, smart care, industrial, etc. In this paper, we present a WSN system based on the ZigBee technology (IEEE 802.15.4) in Smart Home. To have a good sensor networks communication implanted in a smart home, studies of operating performance on this network is important. In this work, we investigate the performance of our ZigBee sensor networks. The study of performance is based on measurements of the Received Signal Strength Indicator (RSSI) in different parts of the Home. We will also discuss the impact of electromagnetic noise on the communication performance of a ZigBee Sensor Network in…
Analysing texture features from individual observer simulations
2021
We investigated the impact of simulated individual observer colour matching functions (CMFs) on computational texture features. We hypothesised that most humans perceive texture in a similar manner, hence a texture indicator that is the least dependent on individual physiology of human vision would be most likely a potential fit to serve as quantified visually perceived texture. To this end, the following strategy was implemented: hyper-spectral image textures were converted into XYZ images for individual observer CMFs, contrast sensitivity function (CSF) filtering was subsequently applied on the XYZ images for visual simulation. Two types of texture features were extracted from the filtere…
On the appearance of objects and materials: Qualitative analysis of experimental observations
2021
Perception of appearance of different materials and objects is a complex psychophysical phenomenon and its neurophysiological and behavioral mechanisms are far from being fully understood. The various appearance attributes are usually studied separately. In addition, no comprehensive and functional total appearance modelling has been done up-to date. We have conducted experiments using physical objects asking observers to describe the objects and carry out visual tasks. The process has been videotaped and analysed qualitatively using the Grounded Theory Analysis, a qualitative research methodology from social science. In this work, we construct a qualitative model of this data and compare i…
VisNIR pigment mapping and re-rendering of an experimental painting
2021
Pigment mapping allows the classification and estimation of the abundances of pigments in paintings. The information learned becomes extremely important for conservators, who are then able to decide the best strategies in the conservation of the artefacts. When the goal is to restore a painting, it is also important to know what the effects of the newly introduced materials are. To fulfil this purpose, a proper mixing model must be defined. We propose a framework to perform pigment mapping on the hyperspectral image of an experimental painting realised for the occasion, with the goal of rendering a colour image using the concentrations retrieved from the mapping. Contrarily to spectral unmi…
Development of new techniques for super-resolution video sequences : Towards a real-time implementation on Smart Camera
2020
These thesis works are part of an european project aiming to design a very hight resolution (8k) video camera. Within this project our team had the task of working on two technological aspects: (1) the design of a demonstrator carrying out a realtime deconvolution of a video stream coming from a very high resolution camera created by the consortium , (2) the design of a prototype allowing to increase the resolution and the level of detail of video streams from an input resolution of 4k to 8k using Super Resolution (SR) methods. This manuscript mainly presents the work related to the creation of the prototype realizing a Super Resolution method. In order to be able to assess the qualitative …
Adéquation Algorithme architecture : Aspects logiciels, matériels et cognitifs
2008
Les travaux présentés dans le cadre de cette Habilitation à Diriger des Recherches s'inscrivent principalement dans la problématique dite d'" Adéquation Algorithme Architecture ". Ils ont pour objectif commun la mise en œuvre de systèmes matériels et logiciels dédiés à la vision artificielle à fortes contraintes temporelles. Ils se focalisent sur différents aspects cruciaux tels que l'acquisition d'images par des capteurs dédiés, le développement et la programmation d'architectures optimisées de traitement des images et l'implantation d'algorithmes de traitement du signal et d'images en temps réel sur ces architectures.
Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency
2018
International audience