Search results for "Signal and Image processing"

Incorporating depth information into few-shot semantic segmentation

2021

International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…

Propagation d'informations le long d'une ligne de transmission non linéaire structurée en super réseau et simulant un neurone myélinisé

2019

Non-linear systems are almostly described by partial differential equations that characterize them. We have some systems such as the chain of coupled pebdelums, the protein chain comprising molecules with hydrogen bonds, atomic lattice, and so on .These systems are most often characterized by anharmonic inter particulate interactions and and then immersed in deformable potential substrates. In addition to nonlinearity and dispersion, these other phenomena namely anharmonicity and deformability are responsible for certain properties of propagation of solitary waves such as (compactons, kinks and anti-kinks, peackons, ...etc) and also the ability of the systems to transmit a signal . We used …

Interactive evolution for cochlear implants fitting

2007

International audience; Cochlear implants are devices that become more and more sophisticated and adapted to the need of patients, but at the same time they become more and more difficult to parameterize. After a deaf patient has been surgically implanted, a specialised medical practitioner has to spend hours during months to precisely fit the implant to the patient. This process is a complex one implying two intertwined tasks: the practitioner has to tune the parameters of the device (optimisation) while the patient's brain needs to adapt to the new data he receives (learning). This paper presents a study that intends to make the implant more adaptable to environment (auditive ecology) and…

Deep learning for dehazing: Benchmark and analysis

2018

International audience; We compare a recent dehazing method based on deep learning , Dehazenet, with traditional state-of-the-art approach, on benchmark data with reference. Dehazenet estimates the depth map from a single color image, which is used to inverse the Koschmieder model of imaging in the presence of haze. In this sense, the solution is still attached to the Koschmieder model. We demonstrate that this method exhibits the same limitation than other inversions of this imaging model.

Une architecture programmable de traitement des impulsions zéro-temps mort pour l'instrumentation nucléaire

2015

In the field of nuclear instrumentation, digital signal processing architectures have to deal with the poissonian characteristic of the signal, composed of random arrival pulses which requires current architectures to work in dataflow. Thus, the real-time needs implies losing pulses when the pulse rate is too high. Current architectures paralyze the acquisition of the signal during the pulse processing inducing a time during no signal can be processed, this is called the dead time. These issue have led current architectures to use dedicated solutions based on reconfigurable components such as FPGAs. The requirement of end users to implement a wide range of applications on a large number of …

PROCEDE DE PRE-DISTORSION NUMERIQUE D’UN SIGNAL ET REPETEUR DE TELECOMMUNICATION INTEGRANT UN FILTRE A REPONSE IMPULSIONNELLE FINIE POUR METTRE EN OE…

2013

L'invention concerne un procédé de pré-distorsion numérique d'un signal de télécommunication traité dans un circuit électronique 100 intégrant un filtre à réponse impulsionnelle finie 321. Ce procédé consiste successivement: - à identifier, à la sortie du circuit 100, les paramètres de distorsions de phase et/ou d'amplitude du signal en fonction de la fréquence, - à partir des susdits paramètres de distorsions relevés, à générer, par un algorithme basé sur une interpolation, des coefficients permettant d'effectuer dans ledit filtre 321, des prédistorsions du signal numérique destinées à engendrer une précorrection des susdites distorsions, - à transférer lesdits coefficients de pré-distorsi…

Learning Bag of Spatio-Temporal Features for Human Interaction Recognition

2019

Bag of Visual Words Model (BoVW) has achieved impressive performance on human activity recognition. However, it is extremely difficult to capture high-level semantic meanings behind video features with this method as the spatiotemporal distribution of visual words is ignored, preventing localization of the interactions within a video. In this paper, we propose a supervised learning framework that automatically recognizes high-level human interaction based on a bag of spatiotemporal visual features. At first, a representative baseline keyframe that captures the major body parts of the interacting persons is selected and the bounding boxes containing persons are extracted to parse the poses o…

Proc. of SPIE, Optics, Photonics, and Digital Technologies for Multimedia Applications II

2012

Online Multi-object Tracking Combining Optical Flow and Compressive Tracking for Intelligent Vehicles

2017

International audience; no abstract

Hybrid Model/data-Driven Fault Detection and Exclusion for a Decentralized Cooperative Multi-Robot System

2022

International audience