Centre dedocumentation
scientifique

Semantic hierarchy emerges in deep generative representations for scene synthesis / Ceyuan Yang in International journal of computer vision, vol 129 n° 5 (May 2021)  

Public [article]  inInternational journal of computer vision > vol 129 n° 5 (May 2021) . - pp 1451 - 1466 Titre : Semantic hierarchy emerges in deep generative representations for scene synthesis Type de document : Article/Communication Auteurs : Ceyuan Yang, Auteur ; Yujun Shen, Auteur ; Bolei Zhou, Auteur Année de publication : 2021 Article en page(s) : pp 1451 - 1466 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse sémantique [Termes IGN] analyse visuelle [Termes IGN] apprentissage profond [Termes IGN] compréhension de l'image [Termes IGN] représentation des connaissances [Termes IGN] Réseau antagoniste génératif [Termes IGN] segmentation hiérarchique [Termes IGN] segmentation sémantique [Termes IGN] synthèse d'image Résumé : (auteur) Despite the great success of Generative Adversarial Networks (GANs) in synthesizing images, there lacks enough understanding of how photo-realistic images are generated from the layer-wise stochastic latent codes introduced in recent GANs. In this work, we show that highly-structured semantic hierarchy emerges in the deep generative representations from the state-of-the-art GANs like StyleGAN and BigGAN, trained for scene synthesis. By probing the per-layer representation with a broad set of semantics at different abstraction levels, we manage to quantify the causality between the layer-wise activations and the semantics occurring in the output image. Such a quantification identifies the human-understandable variation factors that can be further used to steer the generation process, such as changing the lighting condition and varying the viewpoint of the scene. Extensive qualitative and quantitative results suggest that the generative representations learned by the GANs with layer-wise latent codes are specialized to synthesize various concepts in a hierarchical manner: the early layers tend to determine the spatial layout, the middle layers control the categorical objects, and the later layers render the scene attributes as well as the color scheme. Identifying such a set of steerable variation factors facilitates high-fidelity scene editing based on well-learned GAN models without any retraining (code and demo video are available at https://genforce.github.io/higan). Numéro de notice : A2021-408 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11263-020-01429-5 date de publication en ligne : 10/02/2021 En ligne : https://doi.org/10.1007/s11263-020-01429-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97725 [article]

Recognition of varying size scene images using semantic analysis of deep activation maps / Shikha Gupta in Machine Vision and Applications, vol 32 n° 2 (March 2021)  

Public [article]  inMachine Vision and Applications > vol 32 n° 2 (March 2021) . - n° 52 Titre : Recognition of varying size scene images using semantic analysis of deep activation maps Type de document : Article/Communication Auteurs : Shikha Gupta, Auteur ; A.D. Dileep, Auteur ; Veena Thenkanidiyoor, Auteur Année de publication : 2021 Article en page(s) : n° 52 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] analyse sémantique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] compréhension de l'image [Termes IGN] méthode fondée sur le noyau [Termes IGN] modèle conceptuel de données [Termes IGN] reconnaissance de formes Résumé : (auteur) Understanding the complex semantic structure of scene images requires mapping the image from pixel space to high-level semantic space. In semantic space, a scene image is represented by the posterior probabilities of concepts (e.g., ‘car,’ ‘chair,’ ‘window,’ etc.) present in it and such representation is known as semantic multinomial (SMN) representation. SMN generation requires a concept annotated dataset for concept modeling which is infeasible to generate manually due to the large size of databases. To tackle this issue, we propose a novel approach of building the concept model via pseudo-concepts. Pseudo-concept acts as a proxy for the actual concept and gives the cue for its presence instead of actual identity. We propose to use filter responses from deeper convolutional layers of convolutional neural networks (CNNs) as pseudo-concepts, as filters in deeper convolutional layers are trained for different semantic concepts. Most of the prior work considers fixed-size (≈227×227) images for semantic analysis which suppresses many concepts present in the images. In this work, we preserve the true-concept structure in images by passing in their original resolution to convolutional layers of CNNs. We further propose to prune the non-prominent pseudo-concepts, group the similar one using kernel clustering and later model them using a dynamic-based support vector machine. We demonstrate that resulting SMN representation indeed captures the semantic concepts better and results in state-of-the-art classification accuracy on varying size scene image datasets such as MIT67 and SUN397. Numéro de notice : A2021-454 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01168-8 date de publication en ligne : 01/03/2021 En ligne : https://doi.org/10.1007/s00138-021-01168-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97898 [article]

Spatial multi-criteria evaluation in 3D context: suitability analysis of urban vertical development / Kendra Munn in Cartography and Geographic Information Science, vol 48 n° 2 (March 2021)  

Public [article]  inCartography and Geographic Information Science > vol 48 n° 2 (March 2021) . - pp 105 - 123 Titre : Spatial multi-criteria evaluation in 3D context: suitability analysis of urban vertical development Type de document : Article/Communication Auteurs : Kendra Munn, Auteur ; Suzana Dragićević, Auteur Année de publication : 2021 Article en page(s) : pp 105 - 123 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse multicritère [Termes IGN] combinaison linéaire ponderée [Termes IGN] compréhension de l'image [Termes IGN] croissance urbaine [Termes IGN] densification [Termes IGN] hauteur du bâti [Termes IGN] logement [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] planification urbaine [Termes IGN] urbanisme [Termes IGN] Vancouver (Colombie britannique) Résumé : (Auteur) Urban densification is often seen as a process that aims to limit the negative environmental impacts of urban sprawl in rapidly growing cities by prioritizing planning policies stimulating vertical growth (or high-rise development) over expansion along the urban fringe. Densification of major Canadian urban areas has led to the proliferation of high-rises with an increasing proportion of residents occupying these buildings rather than traditional individual housing. Thus, there is a need for analytical methods that can evaluate the suitability of different residential units in vertical urban developments based on unique criteria for different stakeholders such as prospective residents, developers, or municipal planners. Multi-criteria evaluation (MCE) analysis with weighted linear combination (WLC) is frequently implemented in geographic information systems (GIS) to identify the appropriate solution(s) for a decision problem. However, there are currently no available MCE methods for spatial analysis that can provide evaluation in a three-dimensional (3D) GIS environment, such as for urban vertical development. Therefore, the main objective of this study is to propose a 3D WLC-MCE suitability analysis method for suitability of high-rise residential units in a dense urban area. Five preference scenarios were developed and applied to data from City of Vancouver, Canada. The results indicate that south-facing units and units on higher floors generally exhibit higher levels of suitability as they are less affected by the noise and pollution of the urban road network and receive more sunlight and ocean views. The proposed 3D MCE approach can be used for urban planning and property tax assessment. Numéro de notice : A2021-096 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2020.1845981 date de publication en ligne : 03/12/2020 En ligne : https://doi.org/10.1080/15230406.2020.1845981 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97020 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2021021	SL	Revue	Centre de documentation	Revues en salle	Disponible

Activity recognition in residential spaces with Internet of things devices and thermal imaging / Kshirasagar Naik in Sensors, vol 21 n° 3 (February 2021)  

Public [article]  inSensors > vol 21 n° 3 (February 2021) . - n° 988 Titre : Activity recognition in residential spaces with Internet of things devices and thermal imaging Type de document : Article/Communication Auteurs : Kshirasagar Naik, Auteur ; Tejas Pandit, Auteur ; Nitin Naik, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 988 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] compréhension de l'image [Termes IGN] contrôle par télédétection [Termes IGN] détection d'événement [Termes IGN] espace intérieur [Termes IGN] image RVB [Termes IGN] image thermique [Termes IGN] intelligence artificielle [Termes IGN] internet des objets [Termes IGN] itération [Termes IGN] modèle stéréoscopique [Termes IGN] objet mobile [Termes IGN] reconnaissance automatique [Termes IGN] reconnaissance d'objets [Termes IGN] scène 3D Résumé : (auteur) In this paper, we design algorithms for indoor activity recognition and 3D thermal model generation using thermal images, RGB images, captured from external sensors, and the internet of things setup. Indoor activity recognition deals with two sub-problems: Human activity and household activity recognition. Household activity recognition includes the recognition of electrical appliances and their heat radiation with the help of thermal images. A FLIR ONE PRO camera is used to capture RGB-thermal image pairs for a scene. Duration and pattern of activities are also determined using an iterative algorithm, to explore kitchen safety situations. For more accurate monitoring of hazardous events such as stove gas leakage, a 3D reconstruction approach is proposed to determine the temperature of all points in the 3D space of a scene. The 3D thermal model is obtained using the stereo RGB and thermal images for a particular scene. Accurate results are observed for activity detection, and a significant improvement in the temperature estimation is recorded in the 3D thermal model compared to the 2D thermal image. Results from this research can find applications in home automation, heat automation in smart homes, and energy management in residential spaces. Numéro de notice : A2021-159 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/s21030988 date de publication en ligne : 02/02/2021 En ligne : https://doi.org/10.3390/s21030988 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97075 [article]

X-ModalNet: A semi-supervised deep cross-modal network for classification of remote sensing data / Danfeng Hong in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 12 - 23 Titre : X-ModalNet: A semi-supervised deep cross-modal network for classification of remote sensing data Type de document : Article/Communication Auteurs : Danfeng Hong, Auteur ; Naoto Yokoya, Auteur ; Gui-Song Sia, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 12 - 23 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] apprentissage profond [Termes IGN] apprentissage semi-dirigé [Termes IGN] bruit blanc [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] compréhension de l'image [Termes IGN] image hyperspectrale [Termes IGN] image multibande [Termes IGN] image radar moirée [Termes IGN] image Sentinel-MSI [Termes IGN] scène urbaine [Termes IGN] transmission de données Résumé : (auteur) This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing. A large amount of multi-modal earth observation images, such as multispectral imagery (MSI) or synthetic aperture radar (SAR) data, are openly available on a global scale, enabling parsing global urban scenes through remote sensing imagery. However, their ability in identifying materials (pixel-wise classification) remains limited, due to the noisy collection environment and poor discriminative information as well as limited number of well-annotated training images. To this end, we propose a novel cross-modal deep-learning framework, called X-ModalNet, with three well-designed modules: self-adversarial module, interactive learning module, and label propagation module, by learning to transfer more discriminative information from a small-scale hyperspectral image (HSI) into the classification task using a large-scale MSI or SAR data. Significantly, X-ModalNet generalizes well, owing to propagating labels on an updatable graph constructed by high-level features on the top of the network, yielding semi-supervised cross-modality learning. We evaluate X-ModalNet on two multi-modal remote sensing datasets (HSI-MSI and HSI-SAR) and achieve a significant improvement in comparison with several state-of-the-art methods. Numéro de notice : A2020-544 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.06.014 date de publication en ligne : 11/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.06.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95770 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020093	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Automated terrain feature identification from remote sensing imagery: a deep learning approach / Wenwen Li in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)  

Permalink

Pyramid scene parsing network in 3D: Improving semantic segmentation of point clouds with multi-scale contextual information / Hao Fang in ISPRS Journal of photogrammetry and remote sensing, vol 154 (August 2019)  

Permalink

Exploring semantic elements for urban scene recognition: Deep integration of high-resolution imagery and OpenStreetMap (OSM) / Wenzhi Zhao in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Permalink

BIM-PoseNet: Indoor camera localisation using a 3D indoor model and deep learning from synthetic images / Debaditya Acharya in ISPRS Journal of photogrammetry and remote sensing, vol 150 (April 2019)  

Permalink

Patch-based detection of dynamic objects in CrowdCam images / Gagan Kanojia in The Visual Computer, vol 35 n° 4 (April 2019)  

Permalink

Vehicle detection in aerial images / Michael Ying Yang in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 4 (avril 2019)  

Permalink

Semantic understanding of scenes through the ADE20K dataset / Bolei Zhou in International journal of computer vision, vol 127 n° 3 (March 2019)  

Permalink

Complete 3D scene parsing from an RGBD image / Chuhang Zou in International journal of computer vision, vol 127 n° 2 (February 2019)  

Permalink

Détection et localisation d'objets 3D par apprentissage profond en topologie capteur / Pierre Biasutti (2019)    

Permalink

Estimation de profondeur à partir d'images monoculaires par apprentissage profond / Michel Moukari (2019)  

Permalink