Search results for "Computer Vision and Pattern Recognition"

showing 10 items of 997 documents

Noise Filtering Using Edge-Driven Adaptive Anisotropic Diffusion

2008

This paper presents a method aimed to noise removal in MRI (Magnetic Resonance Imaging). We propose an improvement of Perona and Malik's anisotropic diffusion filter. In our schema, the diffusion equation of the filter has been modified to take into account the edges direction, This allows the filter to blur uniform areas, while it better preserves the edges. Both quantitative and qualitative evaluation is presented and the results are compared with other methods.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniNoise Removal Magnetic Resonance Images Anisotropic Diffusion Brain MRIDiffusion equationNoise measurementComputer scienceAnisotropic diffusionWiener filterComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFilter (signal processing)Edge-preserving smoothingMagnetic fieldAdaptive filtersymbols.namesakeComputer Science::Computer Vision and Pattern RecognitionsymbolsAlgorithm2008 21st IEEE International Symposium on Computer-Based Medical Systems
researchProduct

Pedestrian Tracking in 360 Video by Virtual PTZ Cameras

2018

Since the data acquired by a PTZ camera change while adjusting the pan, tilt and zoom parameters, the results of tracking algorithms are difficult to reproduce; such diffi- culty limits the development and the comparison of tracking algorithms with PTZ cameras. The recently introduced 360- degree cameras acquire spherical views of the environment, generally stored as equirectangular images. Each pixel of an equirectangular image corresponds to a point on the spherical surface. A gnomonic projection can be used to project the points on the spherical surface onto a plane tangent to the sphere. Such tangent plane can be interpreted as the image plane of a virtual PTZ camera oriented towards th…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPixelComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage planeTracking (particle physics)Gnomonic projectionAppearance models Dynamic memory Pedestrian tracking Spherical surface Tracking algorithm Tracking by detections Virtual cameraComputer Science::Computer Vision and Pattern RecognitionEquirectangular projectionComputer visionDevelopment (differential geometry)Artificial intelligenceZoombusinessTilt (camera)2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI)
researchProduct

Real-time content-aware image resizing using reduced linear model

2010

In this paper an effective and efficient method for contentaware image resizing is proposed. It is based on the solution of a linear system where each pixel displacement (compression or expansion) is determined in dependence of the visual relevance of the pixel itself. The linear nature of the model allows real-time application of the method even for large images. This fully automatic approach can be also improved by interactively providing cues such as geometric constraints and/or manual relevant object labeling. The results have proven that the presented method achieves results comparable or superior to existent strategies, while improving efficiency.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPixelImage resizing Image retargeting linear optimization visual saliencyPhysics::Instrumentation and Detectorsbusiness.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONLinear modelIterative reconstructionDisplacement (vector)Computer Science::GraphicsSeam carvingComputer Science::Computer Vision and Pattern RecognitionComputer Science::MultimediaComputer visionArtificial intelligencebusinessImage resolutionComputingMethodologies_COMPUTERGRAPHICS2010 IEEE International Conference on Image Processing
researchProduct

Texture Synthesis for Digital Restoration in the Bit-Plane Representation

2007

In this paper we propose a new approach to handle the problem of restoration of grayscale textured images. The purpose is to recovery missing data of a damaged area. The key point is to decompose an image in its bit-planes, and to process bits rather than pixels. We propose two texture synthesis methods for restoration. The first one is a random generation process, based on the conditional probability of bits in the bit-planes. It is designed for images with stochastic textures. The second one is a best-matching method, running on each bit-plane, that is well suited to synthesize periodic patterns. Results are compared with a state-of-the-art restoration algorithm.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPixelbusiness.industryStochastic processComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFilmsHistoric preservationImage enhancementInternetRestorationTexturesGrayscaleImage textureComputer Science::Computer Vision and Pattern RecognitionComputer visionAlgorithm designArtificial intelligencebusinessImage restorationTexture synthesisMathematicsBit plane2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System
researchProduct

Hankelet-based dynamical systems modeling for 3D action recognition

2015

This paper proposes to model an action as the output of a sequence of atomic Linear Time Invariant (LTI) systems. The sequence of LTI systems generating the action is modeled as a Markov chain, where a Hidden Markov Model (HMM) is used to model the transition from one atomic LTI system to another. In turn, the LTI systems are represented in terms of their Hankel matrices. For classification purposes, the parameters of a set of HMMs (one for each action class) are learned via a discriminative approach. This work proposes a novel method to learn the atomic LTI systems from training data, and analyzes in detail the action representation in terms of a sequence of Hankel matrices. Extensive eval…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSequenceMarkov chainDynamical systems theorySupervised learningHankel MatrixHidden Markov ModelLTI system theoryDiscriminative learningLinear time invariant systemDiscriminative modelActionComputer Science::Systems and ControlControl theorySignal ProcessingComputer Vision and Pattern RecognitionElectrical and Electronic EngineeringHidden Markov modelHankel matrixAlgorithmMathematicsImage and Vision Computing
researchProduct

Wi-Dia: Data-Driven Wireless Diagnostic Using Context Recognition

2018

The recent densification of Wi-Fi networks is exacerbating the effects of well-known pathologies including hidden nodes and flow starvation. This paper provides an automatic diagnostic tool for detecting the source roots of performance impairments by recognizing the wireless operating context. Our tool for Wi-Fi diagnostic, named Wi-Dia, exploits machine learning methods and uses features related to network topology and channel utilization, without impact on regular network operations and working in real-time. Real-time per-link Wi-Fi diagnosis enables recovering actions for context-specific treatments. Wi-Dia classifier recognizes different classes of interference; it is jointly trained us…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - InformaticaExploitRenewable Energy Sustainability and the EnvironmentComputer sciencebusiness.industryReal-time computingEnergy Engineering and Power TechnologyExperimental dataContext recognitionComputer Science Applications1707 Computer Vision and Pattern RecognitionNetwork topologyIndustrial and Manufacturing EngineeringData modelingData-drivenComputer Networks and CommunicationArtificial IntelligenceWirelessbusinessInstrumentationClassifier (UML)2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI)
researchProduct

An evaluation of recent local image descriptors for real-world applications of image matching

2019

This paper discusses and compares the best and most recent local descriptors, evaluating them on increasingly complex image matching tasks, encompassing planar and non-planar scenarios under severe viewpoint changes. This evaluation, aimed at assessing descriptor suitability for real-world applications, leverages the concept of approximated overlap error as a means to naturally extend to non-planar scenes the standard metric used for planar scenes. According to the evaluation results, most descriptors exhibit a gradual performance degradation in the transition from planar to non-planar scenes. The best descriptors are those capable of capturing well not only the local image context, but als…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - InformaticaImage matchingComputer sciencebusiness.industryVisual descriptorsComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognition02 engineering and technology03 medical and health sciences0302 clinical medicineLocal Image Descriptors; Image MatchingRobustness (computer science)Computer Science::Computer Vision and Pattern RecognitionComputer Science::Multimedia030221 ophthalmology & optometry0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessImage matching Data-driven approach Descriptors Evaluation results Local descriptors Local image descriptors Performance degradation Real-worldScene structure Computer vision
researchProduct

Is There Anything New to Say About SIFT Matching?

2020

SIFT is a classical hand-crafted, histogram-based descriptor that has deeply influenced research on image matching for more than a decade. In this paper, a critical review of the aspects that affect SIFT matching performance is carried out, and novel descriptor design strategies are introduced and individually evaluated. These encompass quantization, binarization and hierarchical cascade filtering as means to reduce data storage and increase matching efficiency, with no significant loss of accuracy. An original contextual matching strategy based on a symmetrical variant of the usual nearest-neighbor ratio is discussed as well, that can increase the discriminative power of any descriptor. Th…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore INF/01 - Informaticabusiness.industryComputer scienceImage matchingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformPattern recognition02 engineering and technologySIFT sGLOH2 Quantization Binary descriptors Symmetric matching Hierarchical cascade filtering Deep descriptors Keypoint patch orientation Approximated overlap errorDiscriminative modelArtificial IntelligenceHistogramComputer data storage0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligenceSIFTsGLOH2quantizationbinary descriptorssymmetric matchinghierarchical cascade filteringdeep descriptorskeypoint patch orientationapproximated overlap errorbusinessQuantization (image processing)SoftwareInternational Journal of Computer Vision
researchProduct

A Low Cost Solution for NOAA Remote Sensing

2018

United States National Oceanic and Atmospheric Administration (NOAA) weather satellites adopt Advanced Very High Resolution Radiometer (AVHRR) sensors to acquire remote sensing data and broadcast Automatic Picture Transmission (APT) images. The orientation of the scan lines is perpendicular to the orbit of the satellite. In this paper we propose a new low cost solution for NOAA remote sensing. More in detail, our method focuses on the possibility of directly sampling the modulated signal and processing it entirely in software enabled by recent breakthroughs on Software Defined Radios (SDR) and CPU computational speed, while keeping the costs extremely low. We aim to achieve good results wit…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSignal processingComputer Networks and CommunicationsComputer science0211 other engineering and technologiesComputer Science Applications1707 Computer Vision and Pattern RecognitionInformation System02 engineering and technologyRemote SensingRemote sensing (archaeology)Signal ProcessingInformation systemCommunications satelliteSatellite CommunicationElectrical and Electronic Engineering021101 geological & geomatics engineeringRemote sensingProceedings of the 7th International Conference on Sensor Networks
researchProduct

Image Segmentation through a Hierarchy of Minimum Spanning Trees

2012

Many approaches have been adopted to solve the problem of image segmentation. Among them a noticeable part is based on graph theory casting the pixels as nodes in a graph. This paper proposes an algorithm to select clusters in the images (corresponding to relevant segments in the image) corresponding to the areas induced in the images through the search of the Minimum Spanning Tree (MST). In particular is is based on a clustering algorithm that extracts clusters computing a hierarchy of Minimum Spanning Trees. The main drawback of this previous algorithm is that the dimension of the cluster is not predictable and a relevant portion of found clusters can be composed by micro-clusters that ar…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSpanning treebusiness.industrySingle-linkage clusteringComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognitionImage segmentationMinimum spanning treeImage SegmentationMinimum Spanning TreesClusteringDistributed minimum spanning treeMinimum spanning tree-based segmentationKruskal's algorithmArtificial IntelligenceComputer Science::Computer Vision and Pattern RecognitionReverse-delete algorithmArtificial intelligencebusinessMathematics
researchProduct