Search results for "methodologies"

showing 10 items of 2106 documents

Support Vector Machines for Crop Classification Using Hyperspectral Data

2003

In this communication, we propose the use of Support Vector Machines (SVM) for crop classification using hyperspectral images. SVM are benchmarked to well–known neural networks such as multilayer perceptrons (MLP), Radial Basis Functions (RBF) and Co-Active Neural Fuzzy Inference Systems (CANFIS). Models are analyzed in terms of efficiency and robustness, which is tested according to their suitability to real–time working conditions whenever a preprocessing stage is not possible. This can be simulated by considering models with and without a preprocessing stage. Four scenarios (128, 6, 3 and 2 bands) are thus evaluated. Several conclusions are drawn: (1) SVM yield better outcomes than neura…

Contextual image classificationArtificial neural networkbusiness.industryComputer scienceHyperspectral imagingFuzzy control systemPerceptronMachine learningcomputer.software_genreFuzzy logicSupport vector machineComputingMethodologies_PATTERNRECOGNITIONRobustness (computer science)Radial basis functionArtificial intelligencebusinesscomputer
researchProduct

The indexing of persons in news sequences using audio-visual data

2004

We describe a video indexing system that automatically searches for a specific person in a news sequence. The proposed approach combines audio and video confidence values extracted from speaker and face recognition analysis. The system also incorporates a shot selection module that seeks for anchors, where the person on the scene is likely speaking. The system has been extensively tested on several news sequences with very good recognition rates.

Contextual image classificationComputer scienceSpeech recognitionSearch engine indexingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSelection (linguistics)Speaker recognitionAudio signal processingcomputer.software_genrecomputerFacial recognition systemElectronic mail2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
researchProduct

Detection of power line insulators on digital images with the use of laser spots

2019

The massive growth of technologies used to register and process digital images allow for their application in evaluating the technical condition of power lines. However, it is not possible without a set of dedicated methods for obtaining diagnostic information based on registered video data. The method described here details the detection of power line insulators in digital images featuring diversified backgrounds using laser spots. The algorithm of detecting an insulator in analysed images is based on testing the digital signal of pixel intensity profiles read between subsequent pairs of laser points in the image. The method is comprised of the following stages: import the image with laser…

Contextual image classificationComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage registration020206 networking & telecommunications02 engineering and technologyLaserObject detectionlaw.inventionMaxima and minimaDigital imageElectric power transmissionlawSignal ProcessingDigital image processing0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionComputer Vision and Pattern RecognitionArtificial intelligenceElectrical and Electronic EngineeringbusinessSoftwareIET Image Processing
researchProduct

Real-time image segmentation for anomalies detection using SVM approximation

2003

In this paper, we propose a method of implementation improvement of the decision rule of the support vector machine, applied to real-time image segmentation. We present very high speed decisions (approximately 10 ns per pixel) which can be useful for detection of anomalies on manufactured parts. We propose an original combination of classifiers allowing fast and robust classification applied to image segmentation. The SVM is used during a first step, pre-processing the training set and thus rejecting any ambiguities. The hyperrectangles-based learning algorithm is applied using the SVM classified training set. We show that the hyperrectangle method imitates the SVM method in terms of perfor…

Contextual image classificationPixelArtificial neural networkImage qualitybusiness.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationPattern recognitionImage segmentationSupport vector machineHyperrectangleComputer visionArtificial intelligencebusinessSPIE Proceedings
researchProduct

Large scale semi-supervised image segmentation with active queries

2011

A semiautomatic procedure to generate classification maps of remote sensing images is proposed. Starting from a hierarchical unsupervised classification, the algorithm exploits the few available labeled pixels to assign each cluster to the most probable class. For a given amount of labeled pixels, the algorithm returns a classified segmentation map, along with confidence levels of class membership for each pixel. Active learning methods are used to select the most informative samples to increase confidence in the class membership. Experiments on a AVIRIS hyperspectral image confirm the effectiveness of the method, especially when used with active learning query functions and spatial regular…

Contextual image classificationPixelbusiness.industryComputer scienceHyperspectral imagingPattern recognitionImage segmentationRegularization (mathematics)Statistical classificationComputingMethodologies_PATTERNRECOGNITIONLife ScienceSegmentationArtificial intelligencebusinessCluster analysis
researchProduct

A note on the iterative object symmetry transform

2004

This paper introduces a new operator named the iterated object transform that is computed by combining the object symmetry transform with the morphological operator erosion. This new operator has been applied on both binary and gray levels images showing the ability to grasp the internal structure of a digital object. We present also some experiments on artificial and real images and potential applications.

Contextual image classificationbusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONTop-hat transformMathematical morphologyErosion (morphology)Object (computer science)Real imageOperator (computer programming)Artificial IntelligenceSignal ProcessingComputer visionComputer Vision and Pattern RecognitionArtificial intelligenceSymmetry (geometry)businessSoftwareMathematicsPattern Recognition Letters
researchProduct

Encoding Invariances in Remote Sensing Image Classification With SVM

2013

This letter introduces a simple method for including invariances in support-vector-machine (SVM) remote sensing image classification. We design explicit invariant SVMs to deal with the particular characteristics of remote sensing images. The problem of including data invariances can be viewed as a problem of encoding prior knowledge, which translates into incorporating informative support vectors (SVs) that better describe the classification problem. The proposed method essentially generates new (synthetic) SVs from the obtained by training a standard SVM with the available labeled samples. Then, original and transformed SVs are used for training the virtual SVM introduced in this letter. W…

Contextual image classificationbusiness.industryPattern recognitionInvariant (physics)Geotechnical Engineering and Engineering GeologySupport vector machineComputingMethodologies_PATTERNRECOGNITIONRobustness (computer science)Computer visionArtificial intelligenceElectrical and Electronic EngineeringbusinessMathematicsRemote sensingIEEE Geoscience and Remote Sensing Letters
researchProduct

Automatic Processing Scheme for Low Laser Invasiveness Electro Optical Frequency Mapping mode

2016

International audience; Electro optical techniques are efficient backside contactless techniques usually used for design debug and defect location in modern VLSI. Unfortunately, the signal to noise ratio is quite low and depends on laser power with potential device stress due to long acquisition time or high laser power, especially in up to date technologies. Under these conditions, to maintain a good signal or image quality, specific signal or image processing techniques can be implemented. In this paper, we proposed a new spatial filtering by stationary wavelets and contrast enhancement which allows the use of low laser power and short acquisition time in image mode.

Contrast enhancementImage qualityComputer science[SPI] Engineering Sciences [physics]Wavelet shrinkageComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONEOFMImage processing02 engineering and technology01 natural sciencesSignallaw.invention[SPI]Engineering Sciences [physics]Image modeSignal-to-noise ratiolaw0103 physical sciences0202 electrical engineering electronic engineering information engineeringElectronic engineering[ SPI ] Engineering Sciences [physics]EOPLaser power scalingStationary Wavelet Transform010302 applied physicsSpatial filter020208 electrical & electronic engineeringLaser[SPI.TRON] Engineering Sciences [physics]/Electronics[ SPI.TRON ] Engineering Sciences [physics]/Electronics[SPI.TRON]Engineering Sciences [physics]/ElectronicsFiltering
researchProduct

A navigation and control algorithm for the position tracking of underwater vehicles

2014

In this paper we consider position control of underwater vehicles through inversion of differential kinematics based on uncalibrated, relative to the water, velocity sensors and unknown marine current. An estimation algorithm, based on the above measurements, estimates calibration parameters and marine current, assuring convergence of the estimated velocities to the true quantities. A kinematic control algorithm assures convergence to zero of the position tracking error. An extension of the basic estimation algorithm has been considered, in which position measurements are considered sampled at low rate and randomly spaced in time. Computer simulations are given of the proposed position trac…

Control algorithmUnderactuationComputer sciencebusiness.industryPosition trackingTracking systemInversion (meteorology)KinematicsVehicles Vectors Estimation Kinematics Calibration Mathematical model NavigationComputer Science::RoboticsSettore ING-INF/04 - AutomaticaControl theoryUnderwaterbusinessPosition controlComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Reliable Planar Object Pose Estimation in Light Fields From Best Subaperture Camera Pairs

2018

International audience; A light-field camera can obtain richer information about a scene than a usual camera. This property offers a lot of potential for robot vision. In this paper, we present a method for pose estimation of a planar object with a light-field camera. The light-field camera can be regarded as a set of sub-aperture cameras. Although any combination of them can theoretically be used for the pose estimation, the accuracy depends on the combination. We show that the estimated pose error can be reduced by selecting the best pair of sub-aperture cameras. We have evaluated the accuracy of our approach with real experiments using a light-field camera in front of planar targets held…

Control and OptimizationComputer scienceProperty (programming)Biomedical EngineeringComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSet (abstract data type)PlanarArtificial Intelligence[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionPoseComputer Science::DatabasesGround truthbusiness.industryMechanical EngineeringAstrophysics::Instrumentation and Methods for Astrophysics[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]16. Peace & justiceObject (computer science)Computer Science ApplicationsHuman-Computer InteractionControl and Systems EngineeringComputer Science::Computer Vision and Pattern RecognitionComputer Vision and Pattern RecognitionArtificial intelligencebusiness
researchProduct