Search results for "RGB"

showing 10 items of 116 documents

Chess recognition using 3D patterned illumination camera

2021

Computer Vision has been applied to augment traditional board games such as Chess for a number of reasons. While augmented reality enhances the gaming experience, the required additional hardware (e.g. head gear) is still not widely accepted in everyday leisure activities, and therefore, camera based methods have been developed to interface the computer with the real-life chess board. However, traditional 2D camera approaches suffer from ill-defined environmental conditions (lighting, viewing angle) and are therefore severely limited in their application. To answer this issue, we have incorporated a consumer-grade depth camera based on patterned illumination. We could show that in combinati…

Computer programComputer sciencebusiness.industryHead (linguistics)Interface (computing)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputingMilieux_PERSONALCOMPUTINGRGB color modelAugmented realityComputer visionArtificial intelligenceViewing anglebusinessThirteenth International Conference on Machine Vision
researchProduct

Automatic Calibration of an Industrial RGB-D Camera Network Using Retroreflective Fiducial Markers

2019

This paper describes a non-invasive, automatic, and robust method for calibrating a scalable RGB-D sensor network based on retroreflective ArUco markers and the iterative closest point (ICP) scheme. We demonstrate the system by calibrating a sensor network comprised of six sensor nodes positioned in a relatively large industrial robot cell with an approximate size of 10 m × 10 m × 4 m . Here, the automatic calibration achieved an average Euclidean error of 3 c m at distances up to 9.45 m . To achieve robustness, we apply several innovative techniques: Firstly, we mitigate the ambiguity problem that occurs when detecting a marker at long range or low resolution by comparing the…

Computer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologylcsh:Chemical technologytime-of-flightBiochemistryArticleVDP::Food science and technology: 600Analytical Chemistrylaw.inventionIndustrial robotlawRegion of interestRobustness (computer science)automatic calibration0202 electrical engineering electronic engineering information engineeringCalibrationVDP::Næringsmiddelteknologi: 600lcsh:TP1-1185Computer visionElectrical and Electronic EngineeringInstrumentationbusiness.industryambiguity problemIterative closest point3D sensors020207 software engineeringretroreflective markersAtomic and Molecular Physics and OpticsTime of flightTheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESRGB color model020201 artificial intelligence & image processingArtificial intelligencebusinessFiducial markerWireless sensor networkSensors
researchProduct

Visual Marker Guided Point Cloud Registration in a Large Multi-Sensor Industrial Robot Cell

2018

This paper presents a benchmark and accuracy analysis of 3D sensor calibration in a large industrial robot cell. The sensors used were the Kinect v2 which contains both an RGB and an IR camera measuring depth based on the time-of-flight principle. The approach taken was based on a novel procedure combining Aruco visual markers, methods using region of interest and iterative closest point. The calibration of sensors is performed pairwise, exploiting the fact that time-of-flight sensors can have some overlap in the generated point cloud data. For a volume measuring 10m × 14m × 5m a typical accuracy of the generated point cloud data of 5–10cm was achieved using six sensor nodes.

Computer sciencebusiness.industry010401 analytical chemistryPoint cloudIterative closest pointCloud computing02 engineering and technology01 natural sciences0104 chemical sciencesVisualizationlaw.inventionIndustrial robotlaw0202 electrical engineering electronic engineering information engineeringBenchmark (computing)CalibrationRGB color model020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)
researchProduct

Robust Hand Gestures Recognition Using a Deep CNN and Thermal Images

2021

Medical systems and assistive technologies, human-computer interaction, human-robot interaction, industrial automation, virtual environment control, sign language translation, crisis and disaster management, entertainment and computer games, and so on all use RGB cameras for hand gesture recognition. However, their performance is limited especially in low-light conditions. In this paper, we propose a robust hand gesture recognition system based on high-resolution thermal imaging that is light-independent. A dataset of 14,400 thermal hand gestures is constructed, separated into two color tones. We also propose using a deep CNN to classify high-resolution hand gestures accurately. The propose…

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONSign languagecomputer.software_genreAutomationVirtual machineGesture recognitionBenchmark (computing)RGB color modelComputer visionArtificial intelligenceElectrical and Electronic EngineeringbusinessInstrumentationcomputerEdge computingGestureIEEE Sensors Journal
researchProduct

Three-domain image representation for personal photo album management

2010

In this paper we present a novel approach for personal photo album management. Pictures are analyzed and described in three representation spaces, namely, faces, background and time of capture. Faces are automatically detected and rectified using a probabilistic feature extraction technique. Face representation is then produced by computing PCA (Principal Component Analysis). Backgrounds are represented with low-level visual features based on RGB histogram and Gabor filter bank. Temporal data is obtained through the extraction of EXIF (Exchangeable image file format) data. Each image in the collection is then automatically organized using a mean-shift clustering technique. While many system…

Computer sciencebusiness.industryFeature extractionCBIR - Content Based Image Retrieval automatic image annotation personal photo album managementComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processingcomputer.file_formatGabor filterAutomatic image annotationHistogramFace (geometry)RGB color modelComputer visionArtificial intelligenceImage file formatsImage sensorCluster analysisbusinesscomputer
researchProduct

Bag of words representation and SVM classifier for timber knots detection on color images

2015

Knots as well as their density have a huge impact on the mechanical properties of wood boards. This paper addresses the issue of their automatic detection. An image processing pipeline which associates low level processing (contrast enhancement, thresholding, mathematical morphology) with bag-of-words approach is developed. We propose a SVM classification based on features obtained by SURF descriptors on RGB images, followed by a dictionary created using the bag-of-words approach. Our method was tested on color images from two different datasets with a total number of 640 knots. The mean recall (true positive) rate achieved was (92%) and (97%) for a single dictionary (built only on samples …

Computer sciencebusiness.industryFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processingPattern recognitionMathematical morphologyThresholdingSupport vector machineComputingMethodologies_PATTERNRECOGNITIONBag-of-words modelHistogramRGB color modelComputer visionArtificial intelligencebusiness2015 14th IAPR International Conference on Machine Vision Applications (MVA)
researchProduct

Towards single snapshot multispectral skin assessment

2012

Skin assessment technology based on comparative analysis of single-pixel RGB signal values at poly-chromatic illumination has been proposed. Multi-spectral imaging information from a single snapshot RGB image data set with the inter-channel crosstalk correction can be extracted this way. Proof-of-concept evaluations and measurement results are presented and discussed. Potential of bi-chromatic illumination for skin hemoglobin mapping during arterial occlusion test has been demonstrated.

Computer sciencebusiness.industryMultispectral imageSnapshot (computer storage)RGB color modelComputer visionArtificial intelligencebusinessSPIE Proceedings
researchProduct

Replication Data for: CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening

2021

Dataset used to train and test a human classifier in the article "CNN-based People Detection in Voxel Space using Intensity Measurements and Point Cluster Flattening". The set contains both the raw point cloud data from an outdoor test site, as well as generated images used for training.

DetectionEngineeringComputer and Information ScienceVisionPoint CloudRGB-DClassificationHuman
researchProduct

Tīklenes attēlu analīze diabētiskās retinopātijas radīto tīklenes izmaiņu detektēšanai

2022

Bakalaura darbs ir uzrakstīts angļu valodā uz 42 lappusēm. Tas satur 32 attēlus, 2 tabulas un 59 atsauces uz literatūras avotiem. Darba mērķis bija pārbaudīt, vai pastāv atšķirība starp vidējo pikseļu intensitāti fundusa attēlā, kurā redzama vesela tīklene, un attēlu ar diabētisku retinopātiju. Attēli tika ņemti no divām datu bāzēm, kurās kopumā bija 127 attēli bez patologijam un 129 attēli ar diabētiskās retinopātijas klātbūtni. Attēlu analīzei tika izmantota programma MATLAB. Pētījuma rezultāti parādīja, ka zilajam kanālam ir būtiska atšķirība, bet sarkanajam un zaļajam kanālam nav. Ir jāveic vairāk pētījumu, lai secinātu, vai ir būtiskas atšķirības pikseļu intensitātē veseliem un diabēti…

Diabetic RetinopathyFundus CameraPixel IntensityRGB channelOptometrija
researchProduct

Comparison of single-spot technique and RGB imaging for erythema index estimation

2016

A commercially available point measurement device, the Mexameter(®), and an experimental RGB imaging prototype device were used for erythema index estimation of 50 rosacea patients by analysing the level of skin redness on the forehead, both cheeks and both sides of a nose. Results are compared with Clinician's Erythema Assessment (CEA) values given by two dermatologists. The Mexameter uses 568 nm and 660 nm LEDs and a photodetector for estimation of erythema index, while the used prototype device acquired RGB images at 460 nm, 530 nm and 665 nm LED illumination. Several erythema index estimation algorithms were compared to determine which one gives the best contrast between increased eryth…

Diagnostic Imagingmedicine.medical_specialtyErythemaPhysiologyBiomedical EngineeringBiophysicsColor01 natural sciencesImaging data010309 optics030207 dermatology & venereal diseases03 medical and health sciences0302 clinical medicineMeasurement devicePhysiology (medical)0103 physical sciencesmedicineHumansLed illuminationbusiness.industrymedicine.diseaseDermatologymedicine.anatomical_structureSemiconductorsErythemaRosaceaForeheadRGB color modelFemalemedicine.symptomNormal skinbusinessAlgorithmsPhysiological Measurement
researchProduct