Search results for "Semantic Segmentation"

showing 6 items of 6 documents

Deep multimodal fusion for semantic image segmentation: A survey

2021

International audience; Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in compute…

Computer science02 engineering and technologyMachine learningcomputer.software_genre0202 electrical engineering electronic engineering information engineeringImage fusionSegmentationmutimodal fusionImage segmentationImage fusionHeuristicbusiness.industryDeep learning[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Deep learning020207 software engineeringImage segmentationSemantic segmentationVariety (cybernetics)Multi-modal[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Signal ProcessingBenchmark (computing)020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencePerformance improvementbusinesscomputerImage and Vision Computing
researchProduct

Semantic Analysis of the Driving Environment in Urban Scenarios

2021

Understanding urban scenes require recognizing the semantic constituents of a scene and the complex interactions between them. In this work, we explore and provide effective representations for understanding urban scenes based on in situ perception, which can be helpful for planning and decision-making in various complex urban environments and under a variety of environmental conditions. We first present a taxonomy of deep learning methods in the area of semantic segmentation, the most studied topic in the literature for understanding urban driving scenes. The methods are categorized based on their architectural structure and further elaborated with a discussion of their advantages, possibl…

Deep LearningMotion Compensation[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Conduite AutonomeAttention VisuelleApprentissage ProfondSemantic SegmentationMoving Object DetectionDétection d'objets en MouvementVisual AttentionCompensation de MouvementAutonomous DrivingSegmentation Sémantique
researchProduct

Analyse et fusion d’images multimodales pour la navigation autonome

2021

Robust semantic scene understanding is challenging due to complex object types, as well as environmental changes caused by varying illumination and weather conditions. This thesis studies the problem of deep semantic segmentation with multimodal image inputs. Multimodal images captured from various sensory modalities provide complementary information for complete scene understanding. We provided effective solutions for fully-supervised multimodal image segmentation and few-shot semantic segmentation of the outdoor road scene. Regarding the former case, we proposed a multi-level fusion network to integrate RGB and polarimetric images. A central fusion framework was also introduced to adaptiv…

Multi-ModalApprentissage profond[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Multimodalite[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Image fusionDeep learningSemantic segmentationSegmentation semantiqueFusion d’images
researchProduct

Zero-shot Semantic Segmentation using Relation Network

2021

Zero-shot learning (ZSL) is widely studied in recent years to solve the problem of lacking annotations. Currently, most studies on ZSL are for image classification and object detection. But, zero-shot semantic segmentation, pixel level classification, is still at its early stage. Therefore, this work proposes to extend a zero-shot image classification model, Relation Network (RN), to semantic segmentation tasks. We modified the structure of RN based on other state-of-the-arts semantic segmentation models (i.e. U-Net and DeepLab) and utilizes word embeddings from Caltech-UCSD Birds 200-2011 attributes and natural language processing models (i.e. word2vec and fastText). Because meta-learning …

hahmontunnistus (tietotekniikka)Meta learning (computer science)Computer scienceSemanticscomputer visionlcsh:Telecommunicationmeta-learninglcsh:TK5101-6720SegmentationWord2veczero-shot semantic segmentationkonenäközero-shot learningimage segmentationContextual image classificationbusiness.industrydeep learningPattern recognitionImage segmentationsemantic segmentationObject detectionkoneoppiminenrelation networkArtificial intelligencebusinessWord (computer architecture)
researchProduct

Editorial for the Special Issue “Frontiers in Spectral Imaging and 3D Technologies for Geospatial Solutions”

2019

This Special Issue hosts papers on the integrated use of spectral imaging and 3D technologies in remote sensing, including novel sensors, evolving machine learning technologies for data analysis, and the utilization of these technologies in a variety of geospatial applications. The presented results showed improved results when multimodal data was used in object analysis.

medicine.medical_specialtyGeospatial analysisComputer sciencehyperspectral imagingSciencecomputer.software_genrehyperspectral imaging; point cloud; sensor integration; data fusion; machine learning; deep learning; classification; estimation; semantic segmentation; object detection; point cloud filteringmedicine3D-mallinnussensor integrationpoint cloud filteringdata fusionestimationbusiness.industryDeep learningspektrikuvausQHyperspectral imagingdeep learningobject detectionSensor fusionObject (computer science)Data scienceObject detectionsemantic segmentationSpectral imagingVariety (cybernetics)classificationpoint cloud filteringsegmentointikoneoppiminenmachine learningclassificationGeneral Earth and Planetary SciencesArtificial intelligencekaukokartoitusbusinesscomputerpoint cloudRemote Sensing
researchProduct

Emotions and Activity Recognition System Using Wearable Device Sensors

2021

Nowadays machines have become extremely smart, there are a lot of existing services that seemed to be unexpectable and futuristic decades or even a few years ago. However, artificial intelligence is still far from human intelligence, machines do not have feelings, consciousness, and intuition. How can we help machines to learn about human feelings and understand their needs better? People take their devices wherever they go, what can devices tell us about their owners? Personal preferences and needs are dependent on emotional and situational contexts. Therefore, emotional and activity aware gadgets would be more intuitive and provide more appropriate information to users. Contemporary weara…

paikkatiedotComputer sciencemedia_common.quotation_subjectWearable computertekoälyRecommender systemwearable device sensorslcsh:TelecommunicationActivity recognitiontoimintatunteetHuman–computer interactionlcsh:TK5101-6720emotions recognitionzero-shot semantic segmentationactivity recognitionanturitSituational ethicsimage segmentationWearable technologymedia_commonHuman intelligencebusiness.industrymielialadeep learningliikkeentunnistusmachine learningkoneoppiminenälytuotteetFeelingälytekniikkaConsciousnessbusinesskasvontunnistus (tietotekniikka)fyysinen aktiivisuus2021 28th Conference of Open Innovations Association (FRUCT)
researchProduct