Search results for "GEP"

showing 7 items of 1017 documents

Video Scene analysis for a configurable hardware accelerator dedicated to Smart Camera

2012

International audience; According to the Center for Research and Prevention of Injuries report, fall-caused injuries of elderly people in UE- 27 are five times as frequent as other injury causes which reduce considerably their mobility and independence. Among the diverse applications of computer vision systems, object detection and event recognition are of the most prominent related recognition and motion analysis, that is, researchers had the idea to spread it in fall detection. The fall event, extracted automatically from the video scene represents itself, crucial information that can be used to alert emergency. In this context, visual information on the corresponding scene is highly impo…

smart camera's acceleratorConfigurable motion estimationadaptive video coding performancesFall detectionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[INFO.INFO-ES]Computer Science [cs]/Embedded Systems[ INFO.INFO-ES ] Computer Science [cs]/Embedded Systems[INFO.INFO-ES] Computer Science [cs]/Embedded Systems
researchProduct

Multispectral filter arrays: Recent advances and practical implementation

2014

Thanks to some technical progress in interferencefilter design based on different technologies, we can finally successfully implement the concept of multispectral filter array-based sensors. This article provides the relevant state-of-the-art for multispectral imaging systems and presents the characteristics of the elements of our multispectral sensor as a case study. The spectral characteristics are based on two different spatial arrangements that distribute eight different bandpass filters in the visible and near-infrared area of the spectrum. We demonstrate that the system is viable and evaluate its performance through sensor spectral simulation. Multispectral filter arrays: Recent advan…

snapshotmultispectral imaging[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingComputer scienceMultispectral imageComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologylcsh:Chemical technologycomputer.software_genre01 natural sciencesBiochemistryArticleAnalytical Chemistry010309 opticsBand-pass filter[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing0103 physical sciencesElectronic engineeringlcsh:TP1-1185Electrical and Electronic EngineeringInstrumentationsnapshot multispectral imaging021001 nanoscience & nanotechnologyAtomic and Molecular Physics and Opticssingle solid state sensorspatio-spectral scene samplingComputingMethodologies_PATTERNRECOGNITIONFilter (video)multispectral and color filter arraysData mining0210 nano-technologycomputer
researchProduct

The Radon-Wigner Transform and Its Application to First-order Optical Systems

2009

The Radon-Wigner transform is presented as a tool for the description of 1st-order optical systems. The input/output relationships for this phase-space representation are obtained and their application in analysis and design tasks is pointed out.

symbols.namesakeFourier transformComputer scienceHartley transformComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONsymbolsShort-time Fourier transformHarmonic wavelet transformS transformAlgorithmConstant Q transformDiscrete Fourier transformFractional Fourier transformFrontiers in Optics 2009/Laser Science XXV/Fall 2009 OSA Optics & Photonics Technical Digest
researchProduct

Interface Detection Using a Quenched-Noise Version of the Edwards-Wilkinson Equation

2015

We report here a multipurpose dynamic-interface-based segmentation tool, suitable for segmenting planar, cylindrical, and spherical surfaces in 3D. The method is fast enough to be used conveniently even for large images. Its implementation is straightforward and can be easily realized in many environments. Its memory consumption is low, and the set of parameters is small and easy to understand. The method is based on the Edwards-Wilkinson equation, which is traditionally used to model the equilibrium fluctuations of a propagating interface under the influence of temporally and spatially varying noise. We report here an adaptation of this equation into multidimensional image segmentation, an…

ta113Image segmentationta114DiscretizationInterface (Java)Computer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONobject detectionimage edge detectionImage segmentationComputer Graphics and Computer-Aided DesignGrayscaleGray-scaleObject detectionSurface topographyNoiseMathematical modelThree-dimensional displaysSegmentationTomography3D image processingNoiseSurface morphologyAlgorithmSoftwareIEEE Transactions on Image Processing
researchProduct

Automatic dynamic texture segmentation using local descriptors and optical flow

2012

A dynamic texture (DT) is an extension of the texture to the temporal domain. How to segment a DT is a challenging problem. In this paper, we address the problem of segmenting a DT into disjoint regions. A DT might be different from its spatial mode (i.e., appearance) and/or temporal mode (i.e., motion field). To this end, we develop a framework based on the appearance and motion modes. For the appearance mode, we use a new local spatial texture descriptor to describe the spatial mode of the DT; for the motion mode, we use the optical flow and the local temporal texture descriptor to represent the temporal variations of the DT. In addition, for the optical flow, we use the histogram of orie…

ta113business.industrySegmentation-based object categorizationComputer scienceTexture DescriptorComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONOptical flowScale-space segmentationPattern recognitionImage segmentationComputer Graphics and Computer-Aided DesignImage textureMotion fieldRegion growingComputer Science::Computer Vision and Pattern RecognitionHistogramComputer visionSegmentationArtificial intelligencebusinessSoftwareIEEE Transactions on Image Processing
researchProduct

Skeleton-Based Multiview Reconstruction

2016

International audience; The advantage of skeleton-based 3D reconstruction is to completely generate a single 3D object from well chosen views. Having numerous views is necessary for a reliable reconstruction but projections of skeletons lead to different topologies. We reconstruct 3D objects with curved medial axis (whose topology is a tree) from the perspective skeletons on an arbitrary number of calibrated acquisitions. The main contribution is to estimate the 3D skeleton, from multiple images: its topology is chosen as the closest to those of the perspective skeletons on the set of images, which means that the number of topology changes to map the 3D skeleton topology to topologies on im…

topologyreconstruction[SPI] Engineering Sciences [physics]ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyIterative reconstructionSkeleton (category theory)Network topologyGraph-edit distanceTopology[SPI]Engineering Sciences [physics]Traitement des imagesMedial axis[ INFO.INFO-TI ] Computer Science [cs]/Image Processing0202 electrical engineering electronic engineering information engineering[ SPI ] Engineering Sciences [physics]Traitement du signal et de l'imageComputer visionSynthèse d'image et réalité virtuelleTopology (chemistry)SkeletonMathematicsComputingMethodologies_COMPUTERGRAPHICSbusiness.industry3D reconstructionPerspective (graphical)020207 software engineeringVision par ordinateur et reconnaissance de formesIntelligence artificielle[SPI.TRON] Engineering Sciences [physics]/Electronics[ SPI.TRON ] Engineering Sciences [physics]/Electronics[SPI.TRON]Engineering Sciences [physics]/Electronics[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Shock graphs[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]graph-edit distance020201 artificial intelligence & image processingTopological skeletonArtificial intelligenceShapesReconstructionbusiness
researchProduct

Webcam based display calibration

2012

International audience; We present an automatic method for measuring the tone response curve of display devices based on visual methods, where the eye is replaced by an end-user, uncalibrated camera, such as a webcam. Our approach compares a series of halftoned patches of known covering ratio with a continuous series of tone patches for each ratio. Both patches are shot by a camera that is used as a virtual eye to evaluate the luminance difference. By an iterative process, the continuous tone value is adjusted while compared with the perceived level of the halftoned patch. When the camera does not see any difference between the patches or a minimal difference, the luminance level of the con…

webcam[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processinggenetic structures[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONDisplay calibration[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingComputingMethodologies_COMPUTERGRAPHICShomochromatic luminance matching
researchProduct