Search results for "scene"

showing 10 items of 95 documents

Spatio-temporal saliency detection in dynamic scenes using color and texture features

2014

Visual saliency is an important research topic in the field of computer vision due to its numerouspossible applications. It helps to focus on regions of interest instead of processingthe whole image or video data. Detecting visual saliency in still images has been widelyaddressed in literature with several formulations. However, visual saliency detection invideos has attracted little attention, and is a more challenging task due to additional temporalinformation. Indeed, a video contains strong spatio-temporal correlation betweenthe regions of consecutive frames, and, furthermore, motion of foreground objects dramaticallychanges the importance of the objects in a scene. The main objective o…

Color featureComplex dynamic scenesSpatio-temporal saliencyDynamic texturesFusionPerformance evalutationModèles d'attention visuelle[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
researchProduct

POLARIZATION-BASED CAR DETECTION

2018

International audience; Road scene understanding is a vital task for driving assistance systems. Robust vehicle detection is a precondition for diverse applications particularly for obstacle avoidance and secure navigation. Color images provide limited information about the physical properties of the object. This results in unstable vehicle detection caused mainly from road scene complexity (strong reflexions, noises and radiometric distortions). Instead, polarimetric images, characteristic of the light wave, can robustly describe important physical properties of the object (e.g., the surface geometric structure, material and roughness etc). This modality gives rich physical informations wh…

Computer scienceFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFeature selection02 engineering and technologySurface finish01 natural sciencesroad scenes010309 optics[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]feature selectionRobustness (computer science)0103 physical sciencesObstacle avoidance0202 electrical engineering electronic engineering information engineeringComputer visionpolarizationColor imagebusiness.industryDetector[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Polarization (waves)Car detection020201 artificial intelligence & image processingArtificial intelligencebusinessDPM
researchProduct

Dynamic 3D Scene Reconstruction and Enhancement

2017

International audience; In this paper, we present a 3D reconstruction and enhancement approach for high quality dynamic city scene reconstructions. We first detect and segment the moving objects using 3D Motion Segmenta-tion approach by exploiting the feature trajectories' behaviours. Getting the segmentations of both the dynamic scene parts and the static scene parts, we propose an efficient point cloud registration approach which takes the advantages of 3-point RANSAC and Iterative Closest Points algorithms to produce precise point cloud alignment. Furthermore, we proposed a point cloud smoothing and texture mapping framework to enhance the results of reconstructions for both the static a…

Computer sciencePoint cloudComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technology[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processingRANSACPoint Cloud Registration0202 electrical engineering electronic engineering information engineeringSegmentationComputer vision3D Scene Enhancement[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingComputingMethodologies_COMPUTERGRAPHICSMotion Segmentationbusiness.industry3D reconstruction020207 software engineeringFeature (computer vision)Computer Science::Computer Vision and Pattern Recognition020201 artificial intelligence & image processingArtificial intelligencebusiness3D Reconstruction[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingTexture mappingSmoothing
researchProduct

Dog-bite-related attacks: A new forensic approach

2020

Dog attacks today represent a health hazard considering that prevention strategies have not always been successful. The identification of the dog that attacked the victim is necessary, considering the civil or criminal consequences for the animal's owner. An accurate scene analysis must be performed collecting a series of important information.Forensic investigations in dog attacks involve different methods, such as the evaluating of the canine Short Tandem Repeat (STR) typing in saliva traces on wounds or bite mark analysis, however, these techniques cannot always be applied. The effort to find new methods to identify the dog that attacked the victim represents a very interesting field for…

Computer scienceSample (material)Sensitivity and Specificity01 natural sciencesdog attacksCattle genotypingForensic pathologyPathology and Forensic MedicineGenetic profile03 medical and health sciencesDogs0302 clinical medicinemedicineAnimalsHumansShort tandem repeatBites and Stings030216 legal & forensic medicineSalivacattle genotyping; dog attacks; dog identification; forensic pathology; forensic science; short tandem repeat; tgla122; tgla53Dog attackScene analysisdog identification010401 analytical chemistrytgla53DNAForensic Medicinemedicine.diseaseTGLA53.DNA FingerprintingDog bitePedigree0104 chemical sciencesForensic scienceIdentification (information)TGLA122Reference sampleForensic scienceMedical emergencyDog attackLawForensic Science International
researchProduct

Incomplete 3D motion trajectory segmentation and 2D-to-3D label transfer for dynamic scene analysis

2017

International audience; The knowledge of the static scene parts and the moving objects in a dynamic scene plays a vital role for scene modelling, understanding, and landmark-based robot navigation. The key information for these tasks lies on semantic labels of the scene parts and the motion trajectories of the dynamic objects. In this work, we propose a method that segments the 3D feature trajectories based on their motion behaviours, and assigns them semantic labels using 2D-to-3D label transfer. These feature trajectories are constructed by using the proposed trajectory recovery algorithm which takes the loss of feature tracking into account. We introduce a complete framework for static-m…

Computer scienceScene UnderstandingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technology[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Motion (physics)[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]0502 economics and business0202 electrical engineering electronic engineering information engineering[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionSegmentationMotion Segmentation050210 logistics & transportationbusiness.industry[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO][ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO]05 social sciences3D reconstruction[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]2D to 3D conversionFeature (computer vision)TrajectoryKey (cryptography)Robot020201 artificial intelligence & image processingArtificial intelligence3D Reconstructionbusiness2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
researchProduct

3D Scene Reconstruction Using Kinect

2014

The issue of the automatic reconstruction of 3D scenes has been addressed in several chapters over the last few years. Many of them describe techniques for processing stereo vision or range images captured by high quality range sensors. However, due to the high price of such input devices, most of the methods proposed in the literature are not suitable for real-world scenarios. This chapter proposes a method designed to reconstruct 3D scenes perceived by means of a cheap device, namely the Kinect sensor. The scene is efficiently represented as a composition of superquadric shapes so as to obtain a compact description of environment, however complex it may be. The approach proposed here is i…

Computer sciencebusiness.industrymedia_common.quotation_subjectComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONInput deviceCognitive architectureScene Reconstruction 3D Data KinectReal imageRange (mathematics)StereopsisComputer visionQuality (business)Artificial intelligencebusinessmedia_common
researchProduct

Brian Friel in Spain: An Off-Centre Love Story

2021

Spanish theatres are not prolific in the staging of Irish playwrights. However, the Northern Irish writer Brian Friel (1929-2015) has been a curious exception, his plays having been performed in different cities in Spain since William Layton produced Amantes: vencedores y vencidos (Lovers: Winners and Losers) in 1972. The origin of Friel's popularity in this country may be attributed to what many theatre directors and audiences considered to be a parallel political situation between post-colonial Ireland and the historical peripheral communities with a language other than Spanish: Catalonia, the Basque Country and Galicia; the fact is that the number of Catalan directors who have staged wor…

Cultural Studieslcsh:Language and LiteratureGeneral Arts and Humanitiesmedia_common.quotation_subjecttheatre receptionArt historytranslationArtLove storybrian friellcsh:DA1-995lcsh:Plcsh:History of Great BritainTeatre (Gènere literari) S. XX Història i críticaidentitymedia_commonspanish sceneEstudios Irlandeses
researchProduct

A brief history of the formation of DNA databases in forensic science within Europe.

2001

The introduction of DNA analysis to forensic science brought with it a number of choices for analysis, not all of which were compatible. As laboratories throughout Europe were eager to use the new technology different systems became routine in different laboratories and consequently, there was no basis for the exchange of results. A period of co-operation then started in which a nucleus of forensic scientists agreed on an uniform system. This collaboration spread to incorporate most of the established forensic science laboratories in Europe and continued through two major changes in the technology. At each step agreement was reached on which systems to use. From the beginning it was realise…

Databases FactualInternational CooperationLegislationMinisatellite RepeatsBiologycomputer.software_genrePolymerase Chain ReactionSensitivity and SpecificityPathology and Forensic MedicineDNA databaseCrime sceneHumansEthics MedicalDatabaseHistorical ArticleForensic MedicineHistory 20th CenturyDNA FingerprintingForensic scienceEuropeDNA profilingLawcomputerNational DNA databaseNucleic Acid Amplification TechniquesPolymorphism Restriction Fragment LengthCriminal justiceForensic science international
researchProduct

Compréhension de scènes urbaines basées sur la polarisation

2021

Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying challeng…

Deep LearningSegmentation[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]PolarimetryScene Understanding[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Estimation de profondeurDepth EstimationPolarimétrieCompréhension de scènes
researchProduct

Compréhension de scènes urbaines basée sur la polarisation

2021

Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying chall…

Deep LearningSegmentation[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingComputer VisionVision par ordinateurPolarimetryScene understandingDepth estimationEstimation de profondeurPolarimétrieCompréhension de scène
researchProduct