Descripteur
Documents disponibles dans cette catégorie (9863)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Spatial-temporal attentive LSTM for vehicle-trajectory prediction / Rui Jiang in ISPRS International journal of geo-information, vol 11 n° 7 (July 2022)
[article]
Titre : Spatial-temporal attentive LSTM for vehicle-trajectory prediction Type de document : Article/Communication Auteurs : Rui Jiang, Auteur ; Hongyun Xu, Auteur ; Gelian Gong, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 354 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] données spatiotemporelles
[Termes IGN] navigation autonome
[Termes IGN] relation spatiale
[Termes IGN] système de transport intelligent
[Termes IGN] trajectoire (véhicule non spatial)
[Termes IGN] vision par ordinateurRésumé : (auteur) Vehicle-trajectory prediction is essential for intelligent traffic systems (ITS), as it can help autonomous vehicles to plan a safe and efficient path. However, it is still a challenging task because existing studies have mainly focused on the spatial interactions of adjacent vehicles regardless of the temporal dependencies. In this paper, we propose a spatial-temporal attentive LSTM encoder–decoder model (STAM-LSTM) to predict vehicle trajectories. Specifically, the spatial attention mechanism is used to capture the spatial relationships among neighboring vehicles and then obtain the global spatial feature. Meanwhile, the temporal attention mechanism is designed to distinguish the effects of different historical time steps on future trajectory prediction. In addition, the motion feature of vehicles is extracted to reveal the influence of dynamic information on vehicle-trajectory prediction, and is combined with the local and global spatial features to represent the integrated features of the target vehicle at each historical moment. The experiments were conducted on public highway trajectory datasets—US-101 and I-80 in NGSIM—and the results demonstrate that our model achieves state-of-the-art prediction performance. Numéro de notice : A2022-549 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi11070354 Date de publication en ligne : 21/06/2022 En ligne : https://doi.org/10.3390/ijgi11070354 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101150
in ISPRS International journal of geo-information > vol 11 n° 7 (July 2022) . - n° 354[article]Street-view imagery guided street furniture inventory from mobile laser scanning point clouds / Yuzhou Zhou in ISPRS Journal of photogrammetry and remote sensing, vol 189 (July 2022)
[article]
Titre : Street-view imagery guided street furniture inventory from mobile laser scanning point clouds Type de document : Article/Communication Auteurs : Yuzhou Zhou, Auteur ; Xu Han, Auteur ; Mingjun Peng, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 63 - 77 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] détection d'objet
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] image Streetview
[Termes IGN] instance
[Termes IGN] inventaire
[Termes IGN] jeu de données localisées
[Termes IGN] masque
[Termes IGN] mobilier urbain
[Termes IGN] segmentation sémantique
[Termes IGN] semis de points
[Termes IGN] séparateur à vaste marge
[Termes IGN] Shanghai (Chine)
[Termes IGN] Wuhan (Chine)Résumé : (auteur) Outdated or sketchy inventory of street furniture may misguide the planners on the renovation and upgrade of transportation infrastructures, thus posing potential threats to traffic safety. Previous studies have taken their steps using point clouds or street-view imagery (SVI) for street furniture inventory, but there remains a gap to balance semantic richness, localization accuracy and working efficiency. Therefore, this paper proposes an effective pipeline that combines SVI and point clouds for the inventory of street furniture. The proposed pipeline encompasses three steps: (1) Off-the-shelf street furniture detection models are applied on SVI for generating two-dimensional (2D) proposals and then three-dimensional (3D) point cloud frustums are accordingly cropped; (2) The instance mask and the instance 3D bounding box are predicted for each frustum using a multi-task neural network; (3) Frustums from adjacent perspectives are associated and fused via multi-object tracking, after which the object-centric instance segmentation outputs the final street furniture with 3D locations and semantic labels. This pipeline was validated on datasets collected in Shanghai and Wuhan, producing component-level street furniture inventory of nine classes. The instance-level mean recall and precision reach 86.4%, 80.9% and 83.2%, 87.8% respectively in Shanghai and Wuhan, and the point-level mean recall, precision, weighted coverage all exceed 73.7%. Numéro de notice : A2022-403 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2022.04.023 Date de publication en ligne : 12/05/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.04.023 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100711
in ISPRS Journal of photogrammetry and remote sensing > vol 189 (July 2022) . - pp 63 - 77[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-2022071 SL Revue Centre de documentation Revues en salle Disponible Validation of regional and global ionosphere maps from GNSS measurements versus IRI2016 during different magnetic activity / Ahmed Sedeek in Journal of applied geodesy, vol 16 n° 3 (July 2022)
[article]
Titre : Validation of regional and global ionosphere maps from GNSS measurements versus IRI2016 during different magnetic activity Type de document : Article/Communication Auteurs : Ahmed Sedeek, Auteur Année de publication : 2022 Article en page(s) : pp 229 - 240 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] Afrique du nord
[Termes IGN] données GNSS
[Termes IGN] harmonique sphérique
[Termes IGN] International Reference Ionosphere
[Termes IGN] interpolation
[Termes IGN] Matlab
[Termes IGN] modèle ionosphérique
[Termes IGN] station GNSS
[Termes IGN] teneur verticale totale en électronsRésumé : (auteur) This manuscript explores the divergence of the Vertical Total Electron Content (VTEC) estimated from Global Navigation Satellite System (GNSS) measurements using global, regional, and International Reference Ionosphere (IRI) models over low to high latitude regions during various magnetic activity. The VTEC is estimated using a territorial network consisting of 7 GNSS stations in Egypt and 10 GNSS stations from the International GNSS Service (IGS) Global network. The impact of magnetic activity on VTEC is investigated. Due to the deficiency of IGS receivers in north Africa and the shortage of GNSS measurements, an extra high interpolation is done to cover the deficit of data over North Africa. A MATLAB code was created to produce VTEC maps for Egypt utilizing a territorial network contrasted with global maps of VTEC, which are delivered by the Center for Orbit Determination in Europe (CODE). Thus we can have genuine VTEC maps estimated from actual GNSS measurements over any region of North Africa. A Spherical Harmonics Expansion (SHE) equation was modelled using MATLAB and called Local VTEC Model (LVTECM) to estimate VTEC values using observations of dual-frequency GNSS receivers. The VTEC calculated from GNSS measurement using LVTECM is compared with CODE VTEC results and IRI-2016 VTEC model results. The analysis of outcomes demonstrates a good convergence between VTEC from CODE and estimated from LVTECM. A strong correlation between LVTECM and CODE reaches about 96 % and 92 % in high and low magnetic activity, respectively. The most extreme contrasts are found to be 2.5 TECu and 1.3 TECu at high and low magnetic activity, respectively. The maximum discrepancies between LVTECM and IRI-2016 are 9.7 TECu and 2.3 TECu at a high and low magnetic activity. Variation in VTEC due to magnetic activity ranges from 1–5 TECu in moderate magnetic activity. The estimated VTEC from the regional network shows a 95 % correlation between the estimated VTEC from LVTECM and CODE with a maximum difference of 5.9 TECu. Numéro de notice : A2022-495 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1515/jag-2021-0046 Date de publication en ligne : 09/02/2022 En ligne : https://doi.org/10.1515/jag-2021-0046 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100985
in Journal of applied geodesy > vol 16 n° 3 (July 2022) . - pp 229 - 240[article]Encoder-decoder structure with multiscale receptive field block for unsupervised depth estimation from monocular video / Songnan Chen in Remote sensing, Vol 14 n° 12 (June-2 2022)
[article]
Titre : Encoder-decoder structure with multiscale receptive field block for unsupervised depth estimation from monocular video Type de document : Article/Communication Auteurs : Songnan Chen, Auteur ; Junyu Han, Auteur ; Mengxia Tang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 2906 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage non-dirigé
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] couple stéréoscopique
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] image isolée
[Termes IGN] optimisation (mathématiques)
[Termes IGN] profondeur
[Termes IGN] séquence d'images
[Termes IGN] structure-from-motionRésumé : (auteur) Monocular depth estimation is a fundamental yet challenging task in computer vision as depth information will be lost when 3D scenes are mapped to 2D images. Although deep learning-based methods have led to considerable improvements for this task in a single image, most existing approaches still fail to overcome this limitation. Supervised learning methods model depth estimation as a regression problem and, as a result, require large amounts of ground truth depth data for training in actual scenarios. Unsupervised learning methods treat depth estimation as the synthesis of a new disparity map, which means that rectified stereo image pairs need to be used as the training dataset. Aiming to solve such problem, we present an encoder-decoder based framework, which infers depth maps from monocular video snippets in an unsupervised manner. First, we design an unsupervised learning scheme for the monocular depth estimation task based on the basic principles of structure from motion (SfM) and it only uses adjacent video clips rather than paired training data as supervision. Second, our method predicts two confidence masks to improve the robustness of the depth estimation model to avoid the occlusion problem. Finally, we leverage the largest scale and minimum depth loss instead of the multiscale and average loss to improve the accuracy of depth estimation. The experimental results on the benchmark KITTI dataset for depth estimation show that our method outperforms competing unsupervised methods. Numéro de notice : A2022-563 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14122906 En ligne : https://doi.org/10.3390/rs14122906 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101240
in Remote sensing > Vol 14 n° 12 (June-2 2022) . - n° 2906[article]3D modeling method for dome structure using digital geological map and DEM / Xian-Yu Liu in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)
[article]
Titre : 3D modeling method for dome structure using digital geological map and DEM Type de document : Article/Communication Auteurs : Xian-Yu Liu, Auteur ; An-Bo Li, Auteur ; Hao Chen, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 339 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] carte géologique
[Termes IGN] carte stratigraphique
[Termes IGN] courbe de Bézier
[Termes IGN] modèle géologique
[Termes IGN] modèle numérique de surface
[Termes IGN] modélisation 3D
[Termes IGN] structure géologiqueRésumé : (auteur) Geological maps have wide coverage with low acquisition difficulty. When other geological survey data are scarce, they are a valuable source of geological structure information for geological modeling. However, for structures with large deformation, geological map information has difficulty meeting the requirement of its 3D geological modeling. Therefore, this paper takes the dome structure as an example to explore a 3D modeling method based on geological maps, DEM and related geological knowledge. The method includes: (1) adaptively calculating the attitude of points on the stratigraphic boundaries; (2) inferring and generating the bottom boundary of the model from the attitude data of the boundary points; (3) generating the model interface constrained by Bézier curves based on the bottom boundary; (4) generating the top and bottom surfaces of the stratum; and (5) stitching each surface of the geological body to generate the final dome model. Case studies of the dome in Wulongshan in China and the Richat structure in Mauritania show that this method can build a solid model of the dome based only on geological maps and DEM data, whose morphological features are basically consistent with those embodied in the section view or the model generated by traditional methods. Numéro de notice : A2022-482 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3390/ijgi11060339 Date de publication en ligne : 07/06/2022 En ligne : https://doi.org/10.3390/ijgi11060339 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100895
in ISPRS International journal of geo-information > vol 11 n° 6 (June 2022) . - n° 339[article]Adversarial defenses for object detectors based on Gabor convolutional layers / Abdollah Amirkhani in The Visual Computer, vol 38 n° 6 (June 2022)PermalinkArtificial intelligence techniques in extracting building and tree footprints using aerial imagery and LiDAR data / Saeideh Sahebi Vayghan in Geocarto international, vol 37 n° 10 ([01/06/2022])PermalinkAssessing and mapping landslide susceptibility using different machine learning methods / Osman Orhan in Geocarto international, vol 37 n° 10 ([01/06/2022])PermalinkBeyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification / Yongqiang Mao in ISPRS Journal of photogrammetry and remote sensing, vol 188 (June 2022)PermalinkConstraint-based evaluation of map images generalized by deep learning / Azelle Courtial in Journal of Geovisualization and Spatial Analysis, vol 6 n° 1 (June 2022)PermalinkContext-aware network for semantic segmentation toward large-scale point clouds in urban environments / Chun Liu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)PermalinkCoupling graph deep learning and spatial-temporal influence of built environment for short-term bus travel demand prediction / Tianhong Zhao in Computers, Environment and Urban Systems, vol 94 (June 2022)PermalinkDetecting interchanges in road networks using a graph convolutional network approach / Min Yang in International journal of geographical information science IJGIS, vol 36 n° 6 (June 2022)PermalinkDetecting spatiotemporal traffic events using geosocial media data / Shishuo Xu in Computers, Environment and Urban Systems, vol 94 (June 2022)PermalinkDiffusionNet: discretization agnostic learning on surfaces / Nicholas Sharp in ACM Transactions on Graphics, TOG, Vol 41 n° 3 (June 2022)PermalinkEfficient calculation of distance transform on discrete global grid systems / Meysam Kazemi in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)PermalinkÉvaluation de la qualité de modèles 3D issus de nuages de points / Tania Landes in XYZ, n° 171 (juin 2022)PermalinkExtracting the urban landscape features of the historic district from street view images based on deep learning: A case study in the Beijing Core area / Siming Yin in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)PermalinkFeature-selection high-resolution network with hypersphere embedding for semantic segmentation of VHR remote sensing images / Hanwen Xu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)PermalinkA geospatial workflow for the assessment of public transit system performance using near real-time data / Anastassios Dardas in Transactions in GIS, vol 26 n° 4 (June 2022)PermalinkGIS and machine learning for analysing influencing factors of bushfires using 40-year spatio-temporal bushfire data / Wanqin He in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)PermalinkA GIS-based approach for identification of optimum runoff harvesting sites and storage estimation: a study from Subarnarekha-Kangsabati Interfluve, India / Manas Karmakar in Applied geomatics, vol 14 n° 2 (June 2022)PermalinkGIS-based assessment of long-term traffic accidents using spatiotemporal and empirical Bayes analysis in Turkey / Saffet Erdoğan in Applied geomatics, vol 14 n° 2 (June 2022)PermalinkHyperNet: A deep network for hyperspectral, multispectral, and panchromatic image fusion / Kun Li in ISPRS Journal of photogrammetry and remote sensing, vol 188 (June 2022)PermalinkInvariant structure representation for remote sensing object detection based on graph modeling / Zicong Zhu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)Permalink