Search results for "Computer Vision"

showing 10 items of 2353 documents

Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis

2009

Independent component analysis (ICA) aims at extracting unknown components from multivariate data assuming that the underlying components are mutually independent. This technique has been successfully applied to the recognition and classification of objects. We present a method that combines the benefits of ICA and the ability of the integral imaging technique to obtain 3D information for the recognition of 3D objects with different orientations. Our recognition is also possible when the 3D objects are partially occluded by intermediate objects.

Integral imagingMultivariate statisticsbusiness.industryComputer scienceImage processingPattern recognitionObject (computer science)Independent component analysisAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic MaterialsComputingMethodologies_PATTERNRECOGNITIONOpticsThree dimensional imagingDistortionPattern recognition (psychology)Computer Vision and Pattern RecognitionArtificial intelligencebusinessJournal of the Optical Society of America A
researchProduct

Digital slicing of 3D scenes by Fourier filtering of integral images

2008

We present a novel technique to extract depth information from 3D scenes recorded using an Integral Imaging system. The technique exploits the periodic structure of the recorded integral image to implement a Fourier-domain filtering algorithm. A proper projection of the filtered integral image permits reconstruction of different planes that constitute the 3D scene. The main feature of our method is that the Fourier-domain filtering allows the reduction of out-of-focus information, providing the InI system with real optical sectioning capacity.

Integral imagingOptical sectioningbusiness.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFilter (signal processing)Iterative reconstructionSlicingAtomic and Molecular Physics and OpticsReduction (complexity)symbols.namesakeOpticsFourier transformFeature (computer vision)Computer Science::Computer Vision and Pattern RecognitionsymbolsbusinessProjection (set theory)Optics Express
researchProduct

Orthoscopic long-focal-depth 3D integral imaging

2006

Integral imaging systems are imaging devices that provide 3D images of 3D objects. When integral imaging systems work in their standard configuration the provided reconstructed images are pseudoscopic; that is, are reversed in depth. In this paper we present, a technique for formation of real, undistorted, orthoscopic integral images by direct pickup. The technique is based on the use of a proper relay system and a global mapping of pixels of the elemental-images set. Simulated imaging experiments are presented to support our proposal.

Integral imagingOpticsPixelbusiness.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer visionPickupArtificial intelligenceIterative reconstructionbusinessDisplay deviceSPIE Proceedings
researchProduct

Multidimensional Integral Imaging for Sensing, Visualization, and Recognition in Degraded Environments

2019

An overview of multidimensional integral imaging for sensing, visualization, and recognition in degraded environments is presented. Applications include 3D visualization, photon starved imaging, material inspection, IR imaging, passive depth estimation, automated human gesture recognition, and long-range imaging.

Integral imagingPhotonThree dimensional imagingbusiness.industryGesture recognitionComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer visionArtificial intelligencebusinessPhoton countingVisualizationImaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)
researchProduct

Optimized integral imaging display by global pixel mapping

2006

Integral imaging systems are imaging devices that provide 3D images of 3D objects. When integral imaging systems work in their standard configuration the provided reconstructed images are pseudoscopic; that is, are reversed in depth. In this paper we present a technique for formation of real, undistorted, orthoscopic integral images by direct pickup. The technique is based on a global mapping of pixels of an elemental-images set. Simulated imaging experiments are presented.

Integral imagingPixelComputer sciencePixel mappingbusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImaging spectrometerIterative reconstructionSet (abstract data type)Computer graphics (images)Computer visionPickupArtificial intelligenceImage sensorbusinessSPIE Proceedings
researchProduct

Elemental images for integral-imaging display

2013

One of the differences between the near-field integral imaging (NInI) and the far-field integral imaging (FInI), is the ratio between number of elemental images and number of pixels per elemental image. While in NInI the 3D information is codified in a small number of elemental images (with many pixels each), in FInI the information is codified in many elemental images (with only a few pixels each). The later codification is similar that the one needed for projecting the InI field onto a pixelated display when aimed to build an InI monitor. For this reason, the FInI cameras are specially adapted for capturing the InI field with display purposes. In this contribution we research the relation…

Integral imagingPixelComputer sciencebusiness.industryComputer graphics (images)Computer visionArtificial intelligenceProjection (set theory)businessSPIE Proceedings
researchProduct

Three-dimensional resolvability in an integral imaging system

2012

The concept of three-dimensional (3D) resolvability of an integral imaging system is thoroughly investigated in this research. The general concept of 3D resolution fails to describe the 3D discrimination completely. Then the concepts of the depth-resolution plane and lateral-resolution plane are introduced to show the difference between the conventional 3D spatial resolution and the newly introduced 3D resolvability. Therefore, the different properties of these planes for differentiating lateral spatial variations and axial variations are analyzed in this paper. The theoretical statements are demonstrated experimentally.

Integral imagingPlane (geometry)business.industryComputer scienceResolution (electron density)Integral photographyAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic MaterialsOpticsThree dimensional imagingComputer Vision and Pattern RecognitionThree dimensional televisionbusinessImage resolutionJournal of the Optical Society of America A
researchProduct

Recent Advances in the Capture and Display of Macroscopic and Microscopic 3-D Scenes by Integral Imaging

2017

The capture and display of images of 3-D scenes under incoherent and polychromatic illumination is currently a hot topic of research, due to its broad applications in bioimaging, industrial procedures, military and surveillance, and even in the entertainment industry. In this context, Integral Imaging (InI) is a very competitive technology due to its capacity for recording with a single exposure the spatial-angular information of light-rays emitted by the 3-D scene. From this information, it is possible to calculate and display a collection of horizontal and vertical perspectives with high depth of field. It is also possible to calculate the irradiance of the original scene at different dep…

Integral imagingSingle exposurebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEntertainment industryContext (language use)Òptica Aparells i instrumentsMicroscòpiaGeographyComputer graphics (images)Computer visionArtificial intelligenceDepth of fieldElectrical and Electronic EngineeringbusinessFocus (optics)Imatges ProcessamentComputingMethodologies_COMPUTERGRAPHICSProceedings of the IEEE
researchProduct

Computation of microimages for plenoptic display

2014

We report a new algorithm for the generation of the microimages ready for their projection into an integral imaging monitor. The algorithm is based in the transformation properties of the plenoptic field captured with an array of digital cameras. We show that a small number of cameras can produce the microimages for displaying 3D scenes with resolution and parallax fully adapted to the monitor features.

Integral imagingTransformation (function)Computer sciencebusiness.industryComputationComputer graphics (images)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer visionArtificial intelligenceParallaxProjection (set theory)businessImage resolution2014 International Conference on 3D Imaging (IC3D)
researchProduct

3D integral imaging display by smart pseudoscopic-to-orthoscopic conversion (SPOC).

2010

Previously, we reported a digital technique for formation of real, non-distorted, orthoscopic integral images by direct pickup. However the technique was constrained to the case of symmetric image capture and display systems. Here, we report a more general algorithm which allows the pseudoscopic to orthoscopic transformation with full control over the display parameters so that one can generate a set of synthetic elemental images that suits the characteristics of the Integral-Imaging monitor and permits control over the depth and size of the reconstructed 3D scene.

Integral imagingbusiness.industryComputer scienceAperture synthesisComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONReproducibility of ResultsImage EnhancementSensitivity and SpecificityAtomic and Molecular Physics and OpticsTransformation (function)OpticsImaging Three-DimensionalImage Interpretation Computer-AssistedComputer visionArtificial intelligenceImage sensorbusinessImage resolutionAlgorithmsOptics express
researchProduct