Search results for "gradient"

showing 10 items of 725 documents

Average Performance Analysis of the Stochastic Gradient Method for Online PCA

2019

International audience; This paper studies the complexity of the stochastic gradient algorithm for PCA when the data are observed in a streaming setting. We also propose an online approach for selecting the learning rate. Simulation experiments confirm the practical relevance of the plain stochastic gradient approach and that drastic improvements can be achieved by learning the learning rate.

Computer Science::Machine Learning[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]Computer science0502 economics and business05 social sciencesMathematicsofComputing_NUMERICALANALYSISRelevance (information retrieval)050207 economics010501 environmental sciencesStochastic gradient method01 natural sciencesAlgorithm0105 earth and related environmental sciences
researchProduct

Change-driven Image Architecture on FPGA with adaptive threshold for Optical-Flow Computation

2006

Optical flow computation has been extensively used for object motion estimation in image sequences. However, the results obtained by most optical flow techniques are as accurate as computationally intensive due to the large amount of data involved. A new strategy for image sequence processing has been developed; pixels of the image sequence that significantly change fire the execution of the operations related to the image processing algorithm. The data reduction achieved with this strategy allows a significant optical flow computation speed-up. Furthermore, FPGAs allow the implementation of a custom data-flow architecture specially suited for this strategy. The foundations of the change-dr…

Computer sciencebusiness.industryBinary imageComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONOptical flowImage processingImage segmentationMotion estimationDigital image processingComputer visionArtificial intelligencebusinessImage gradientComputer hardwareFeature detection (computer vision)2006 IEEE International Conference on Reconfigurable Computing and FPGA's (ReConFig 2006)
researchProduct

New systems for extracting 3-D shape information from images

1993

Neural architectures may offer an adequate way to deal with early vision since they are able to learn shape features or classify unknown shapes, generalising the features of a few meaningful examples, with a low computational cost after the training phase. Two different neural approaches are proposed by the authors: the first one consists of a cascaded architecture made up by a first stage named BWE (Boundary Webs Extractor) which is aimed to extract a brightness gradient map from the image, followed by a backpropagation network that estimates the geometric parameters of the object parts present in the perceived scene. The second approach is based on the extraction of the boundary webs map …

Computer sciencebusiness.industryBoundary (topology)Pattern recognitionObject (computer science)BackpropagationExtractorImage (mathematics)SuperquadricsComputer visionArtificial intelligenceD-ShapeBrightness gradientbusiness
researchProduct

Localization and Activity Classification of Unmanned Aerial Vehicle Using mmWave FMCW Radars

2021

In this article, we present a novel localization and activity classification method for aerial vehicle using mmWave frequency modulated continuous wave (FMCW) Radar. The localization and activity classification for aerial vehicle enables the utilization of mmWave Radars in security surveillance and privacy monitoring applications. In the proposed method, Radar’s antennas are oriented vertically to measure the elevation angle of arrival of the aerial vehicle from ground station. The height of the aerial vehicle and horizontal distance of the aerial vehicle from Radar station on ground are estimated using the measured radial range and the elevation angle of arrival. The aerial vehicle’s activ…

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputerApplications_COMPUTERSINOTHERSYSTEMSConvolutional neural networklaw.inventionSupport vector machinelawActivity classificationChirpRange (statistics)Computer visionGradient boostingArtificial intelligenceElectrical and Electronic EngineeringRadarbusinessInstrumentationEdge computingIEEE Sensors Journal
researchProduct

Restoration and Enhancement of Historical Stereo Photos Through Optical Flow

2021

Restoration of digital visual media acquired from repositories of historical photographic and cinematographic material is of key importance for the preservation, study and transmission of the legacy of past cultures to the coming generations. In this paper, a fully automatic approach to the digital restoration of historical stereo photographs is proposed. The approach exploits the content redundancy in stereo pairs for detecting and fixing scratches, dust, dirt spots and many other defects in the original images, as well as improving contrast and illumination. This is done by estimating the optical flow between the images, and using it to register one view onto the other both geometrically …

Computer sciencemedia_common.quotation_subjectNoise reductionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONOptical flow02 engineering and technologyConsistency (database systems)Image restoration0202 electrical engineering electronic engineering information engineeringRedundancy (engineering)Contrast (vision)Computer visionImage restorationmedia_commonSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryOptical flow021001 nanoscience & nanotechnologySensor fusionStereo matchingTransmission (telecommunications)Image denoisingImage enhancementGradient filtering020201 artificial intelligence & image processingArtificial intelligence0210 nano-technologybusiness
researchProduct

Direct chill casting of aluminium alloys under electromagnetic interaction by permanent magnet assembly

2018

Direct chill casting is one of the methods used in industry to obtain good microstructure and properties of aluminium alloys. Nevertheless, for some alloys grain structure is not optimal. In this study, we offer the use of electromagnetic interaction to modify melt convection near the solidification interface. Solidification under various electromagnetic interactions has been widely studied, but usually at low solidification velocity and high thermal gradient. This type of interaction may succeed fragmentation of dendrite arms and transport of solidification nuclei thus leading to improved material structure and properties. Realization of experimental small-scale crystallizer and electromag…

Condensed Matter::Materials ScienceDirect chill castingTemperature gradientDendrite (crystal)Electromagnetic interactionMaterials sciencechemistryMaterial structureAluminiumMagnetchemistry.chemical_elementComposite materialMicrostructureIOP Conference Series: Materials Science and Engineering
researchProduct

Chebyshev’s Method on Projective Fluids

2020

We demonstrate the acceleration potential of the Chebyshev semi-iterative approach for fluid simulations in Projective Dynamics. The Chebyshev approach has been successfully tested for deformable bodies, where the dynamical system behaves relatively linearly, even though Projective Dynamics, in general, is fundamentally nonlinear. The results for more complex constraints, like fluids, with a particular nonlinear dynamical system, remained unknown so far. We follow a method describing particle-based fluids in Projective Dynamics while replacing the Conjugate Gradient solver with Chebyshev’s method. Our results show that Chebyshev’s method can be successfully applied to fluids and potentially…

Conjugate gradient solverComputer sciencesimulace tekutinanimationAcceleration (differential geometry)02 engineering and technologyDynamical systemChebyshev filternonlinear optimization0202 electrical engineering electronic engineering information engineeringanimaceProjective testnelineární optimalizaceprojektivní dynamikaconstraint-based simulationsimulace založená na omezeníMathematical analysis020207 software engineeringComputer Graphics and Computer-Aided DesignComputational MathematicsNonlinear systemprojective dynamicsParticle020201 artificial intelligence & image processingfluid simulationProjective dynamicsSoftware
researchProduct

Unitary Space–Time Constellation Design Based on the Chernoff Bound of the Pairwise Error Probability

2008

Unitary space-time constellation design is considered for noncoherent multiple-antenna communications, where neither the transmitter nor the receiver knows the fading coefficients of the channel. By employing the Clarke's subdifferential theorem of the sum of the kappa largest singular values of a unitary matrix, we present a numerical optimization procedure for finding unitary space-time signal constellations of any dimension. The Chernoff bound of the pairwise error probability is used directly as a design criterion. The constellations are found by performing gradient descent search on a family ldquosurrogaterdquo functions that converge to the maximum pairwise error probability. The comp…

Constellation diagramUnitary matrixLibrary and Information SciencesComputer Science ApplicationsCombinatoricsChannel capacityChernoff boundGradient descentAlgorithmRandom variableDecoding methodsPairwise error probabilityComputer Science::Information TheoryInformation SystemsMathematicsIEEE Transactions on Information Theory
researchProduct

Assessment of ecosystem integrity and service gradients across Europe using the LTER Europe network

2015

Better integration of knowledge from ecological, social and economic science is necessary to advance the understanding and modelling of socio-ecological systems. To model ecosystem integrity (EI) and ecosystem services (ES) at the landscape scale, assessment matrices are commonly used. These matrices assign capacities to provide different services to different land cover types. We revised such an existing matrix and examined the regional heterogeneity in EI and ES provision in Europe and searched for spatial gradients in their provision to elucidate their suitability for large-scale EI and ES mapping in Europe. Overall, 28 sites belonging to the Long-Term Ecological Research network in Euro…

Consumption (economics)Service (business)business.industryEcosystem serviceEcological ModelingEnvironmental resource managementta1172Assessment matrixProvisioningLand coverEcosystem servicesVariable (computer science)CORINE land coverGeographyLong-term ecological monitoring (LTER)Scale (social sciences)Ecosystementa1181EcosystemEcosystem integritySpatial gradientbusiness
researchProduct

Time-harmonic solution for acousto-elastic interaction with controllability and spectral elements

2010

The classical way of solving the time-harmonic linear acousto-elastic wave problem is to discretize the equations with finite elements or finite differences. This approach leads to large-scale indefinite complex-valued linear systems. For these kinds of systems, it is difficult to construct efficient iterative solution methods. That is why we use an alternative approach and solve the time-harmonic problem by controlling the solution of the corresponding time dependent wave equation. In this paper, we use an unsymmetric formulation, where fluid-structure interaction is modeled as a coupling between pressure and displacement. The coupled problem is discretized in space domain with spectral el…

ControllabilityDiscretizationSpectral element methodfluid-structure interactionspectral element methodacoustic wavescoupled problemTime-harmonic solutioncontrollabilityConjugate gradient methodFluid-structure interactionTime domainCoupled problemMathematicsElastic wavesSpectral element methodelastic wavestime-harmonic solutionApplied MathematicsMathematical analysisLinear systemFinite differenceFinite element methodControllabilityComputational MathematicsAcoustic wavesConjugate gradient algorithmconjugate gradient algorithmJournal of Computational and Applied Mathematics
researchProduct