Search results for "Multispectral imagery"

showing 2 items of 2 documents

Indoor spectroradiometric characterization of plastic litters commonly polluting the Mediterranean Sea: toward the application of multispectral image…

2020

AbstractAround 350 million tonnes of plastics are annually produced worldwide. A remarkable percentage of these products is dispersed in the environment, finally reaching and dispersed in the marine environment. Recent field surveys detected microplastics’ concentrations in the Mediterranean Sea. The most commonly polymers found were polyethylene, polypropylene and viscose, ethylene vinyl acetate and polystyrene. In general, the in-situ monitoring of microplastic pollution is difficult and time consuming. The main goals of this work were to spectrally characterize the most commonly polymers and to quantify their spectral separability that may allow to determine optimal band combinations for…

Settore BIO/07 - EcologiaPollutionMicroplastics010504 meteorology & atmospheric sciencesmedia_common.quotation_subjectMultispectral imageOptical spectroscopylcsh:Medicine010501 environmental sciences01 natural sciencesArticleEnvironmental impactMediterranean sealcsh:Science0105 earth and related environmental sciencesmedia_commonRemote sensingMultidisciplinarySpectral signaturelcsh:RSettore ICAR/02 - Costruzioni Idrauliche E Marittime E IdrologiaCharacterization (materials science)Spectroradiometerspectroradiometric characterization sea plastic litters multispectral imageryEnvironmental sciencelcsh:QSatelliteSettore ICAR/06 - Topografia E CartografiaScientific Reports
researchProduct

Remote sensing image segmentation by active queries

2012

Active learning deals with developing methods that select examples that may express data characteristics in a compact way. For remote sensing image segmentation, the selected samples are the most informative pixels in the image so that classifiers trained with reduced active datasets become faster and more robust. Strategies for intelligent sampling have been proposed with model-based heuristics aiming at the search of the most informative pixels to optimize model's performance. Unlike standard methods that concentrate on model optimization, here we propose a method inspired in the cluster assumption that holds in most of the remote sensing data. Starting from a complete hierarchical descri…

Active learningComputer scienceActive learning (machine learning)SvmMultispectral image0211 other engineering and technologies02 engineering and technologyMultispectral imageryClusteringMultispectral pattern recognitionArtificial Intelligence0202 electrical engineering electronic engineering information engineeringSegmentationCluster analysis021101 geological & geomatics engineeringRetrievalPixelbusiness.industryLinkageHyperspectral imagingPattern recognitionRemote sensingSupport vector machineMultiscale image segmentationHyperspectral imageryPixel ClassificationSignal Processing020201 artificial intelligence & image processingHyperspectral Data ClassificationComputer Vision and Pattern RecognitionArtificial intelligencebusinessAlgorithmsSoftwareModel
researchProduct