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]

Parsing of urban facades from 3D point clouds based on a novel multi-view domain / Wei Wang in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 4 (April 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 4 (April 2021) . - pp 283-293 Titre : Parsing of urban facades from 3D point clouds based on a novel multi-view domain Type de document : Article/Communication Auteurs : Wei Wang, Auteur ; Yuan Xu, Auteur ; Yingchao Ren, Auteur ; Gang Wang, Auteur Année de publication : 2021 Article en page(s) : pp 283-293 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse comparative [Termes IGN] apprentissage profond [Termes IGN] données localisées 3D [Termes IGN] façade [Termes IGN] fusion de données [Termes IGN] milieu urbain [Termes IGN] précision de la classification [Termes IGN] segmentation hiérarchique [Termes IGN] segmentation multi-échelle [Termes IGN] semis de points Résumé : (Auteur) Recently, performance improvement in facade parsing from 3D point clouds has been brought about by designing more complex network structures, which cost huge computing resources and do not take full advantage of prior knowledge of facade structure. Instead, from the perspective of data distribution, we construct a new hierarchical mesh multi-view data domain based on the characteristics of facade objects to achieve fusion of deep-learning models and prior knowledge, thereby significantly improving segmentation accuracy. We comprehensively evaluate the current mainstream method on the RueMonge 2014 data set and demonstrate the superiority of our method. The mean intersection-over-union index on the facade-parsing task reached 76.41%, which is 2.75% higher than the current best result. In addition, through comparative experiments, the reasons for the performance improvement of the proposed method are further analyzed. Numéro de notice : A2021-333 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.87.4.283 date de publication en ligne : 01/04/2021 En ligne : https://doi.org/10.14358/PERS.87.4.283 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97531 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021041	SL	Revue	Centre de documentation	Revues en salle	Disponible

The delineation of tea gardens from high resolution digital orthoimages using mean-shift and supervised machine learning methods / Akhtar Jamil in Geocarto international, vol 36 n° 7 ([01/04/2021])  

Public [article]  inGeocarto international > vol 36 n° 7 [01/04/2021] . - pp 758 - 772 Titre : The delineation of tea gardens from high resolution digital orthoimages using mean-shift and supervised machine learning methods Type de document : Article/Communication Auteurs : Akhtar Jamil, Auteur ; Bulent Bayram, Auteur Année de publication : 2021 Article en page(s) : pp 758 - 772 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme de décalage moyen [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage automatique [Termes IGN] arbre de décision [Termes IGN] Camellia sinensis [Termes IGN] classification dirigée [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par réseau neuronal [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] exploitation agricole [Termes IGN] extraction de la végétation [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] orthoimage [Termes IGN] segmentation hiérarchique [Termes IGN] Turquie Résumé : (Auteur) Rize district is an important tea production site in Turkey, which is known for high quality tea. Determining the temporal changes is very crucial from the viewpoint of agricultural management and protection of tea areas. In addition, delineation of tea gardens using photogrammetric evaluation techniques for a single orthoimage takes approximately 8 h of labour work, which is both costly and time-consuming process. To overcome these issues, a method is proposed for demarcation of tea gardens from high-resolution orthoimages. In this article, a hierarchical object-based segmentation using mean-shift (MS) and supervised machine learning (ML) methods are investigated for delineation of tea gardens. First, the MS algorithm was applied to partition the images into homogeneous segments (objects) and then from each segment, various spectral, spatial and textural features were extracted. Finally, four most widely used supervised ML classifiers, support vector machine (SVM), artificial neural network (ANN), random forest (RF), and decision trees (DTs), were selected for classification of objects into tea gardens and other types of trees. Photogrammetrically evaluated tea garden borders were taken as reference data to evaluate the performance of the proposed methods. The experiments showed that all selected supervised classifiers were effective for delineation of the tea gardens from high-resolution images. Numéro de notice : A2021-293 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1622597 date de publication en ligne : 19/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1622597 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97349 [article]

Urban construction waste with VHR remote sensing using multi-feature analysis and a hierarchical segmentation method / Qiang Chen in Remote sensing, vol 13 n° 1 (January 2021)  

Public [article]  inRemote sensing > vol 13 n° 1 (January 2021) . - n° 158 Titre : Urban construction waste with VHR remote sensing using multi-feature analysis and a hierarchical segmentation method Type de document : Article/Communication Auteurs : Qiang Chen, Auteur ; Qianhao Cheng, Auteur ; Jinfei Wang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 158 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse d'image orientée objet [Termes IGN] analyse multicritère [Termes IGN] analyse spectrale [Termes IGN] construction [Termes IGN] déchet [Termes IGN] extraction de traits caractéristiques [Termes IGN] gestion urbaine [Termes IGN] image à très haute résolution [Termes IGN] morphologie [Termes IGN] Pékin (Chine) [Termes IGN] segmentation hiérarchique [Termes IGN] urbanisation Résumé : (auteur) With rapid urbanization, the disposal and management of urban construction waste have become the main concerns of urban management. The distribution of urban construction waste is characterized by its wide range, irregularity, and ease of confusion with the surrounding ground objects, such as bare soil, buildings, and vegetation. Therefore, it is difficult to extract and identify information related to urban construction waste by using the traditional single spectral feature analysis method due to the problem of spectral confusion between construction waste and the surrounding ground objects, especially in the context of very-high-resolution (VHR) remote sensing images. Considering the multi-feature analysis method for VHR remote sensing images, we propose an optimal method that combines morphological indexing and hierarchical segmentation to extract the information on urban construction waste in VHR images. By comparing the differences between construction waste and the surrounding ground objects in terms of the spectrum, geometry, texture, and other features, we selected an optimal feature subset to improve the separability of the construction waste and other objects; then, we established a classification model of knowledge rules to achieve the rapid and accurate extraction of construction waste information. We also chose two experimental areas of Beijing to validate our algorithm. By using construction waste separability quality evaluation indexes, the identification accuracy of construction waste in the two study areas was determined to be 96.6% and 96.2%, the separability indexes of the construction waste and buildings reached 1.000, and the separability indexes of the construction waste and vegetation reached 1.000 and 0.818. The experimental results show that our method can accurately identify the exposed construction waste and construction waste covered with a dust screen, and it can effectively solve the problem of spectral confusion between the construction waste and the bare soil, buildings, and vegetation. Numéro de notice : A2021-073 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs13010158 date de publication en ligne : 05/01/2021 En ligne : https://doi.org/10.3390/rs13010158 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96809 [article]

Structural segmentation and classification of mobile laser scanning point clouds with large variations in point density / Yuan Li in ISPRS Journal of photogrammetry and remote sensing, vol 153 (July 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 153 (July 2019) . - pp 151 - 165 Titre : Structural segmentation and classification of mobile laser scanning point clouds with large variations in point density Type de document : Article/Communication Auteurs : Yuan Li, Auteur ; Bo Wu, Auteur ; Xuming Ge, Auteur Année de publication : 2019 Article en page(s) : pp 151 - 165 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] champ aléatoire conditionnel [Termes IGN] classification [Termes IGN] classification basée sur les régions [Termes IGN] densité des points [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Hong-Kong [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] Paris (75) [Termes IGN] scène urbaine [Termes IGN] segmentation en régions [Termes IGN] segmentation hiérarchique [Termes IGN] segmentation sémantique [Termes IGN] semis de points Résumé : (Auteur) Objects are formed by various structures and such structural information is essential for the identification of objects, especially for street facilities presented by mobile laser scanning (MLS) data with abundant details. However, due to the large volume of data, large variations in point density, noise and complexity of scanned scenes, the achievement of effective decomposition of objects into physical meaningful structures remains a challenge issue. And structural information has been rarely considered to improve the accuracy of distinguishing between objects with global or local similarity, such as traffic signs and traffic lights. Therefore, we propose a structural segmentation and classification method for MLS point clouds that is efficient and robust to variations in point density and complex urban scenes. During the segmentation stage, a novel region growing approach and a multi-size supervoxel segmentation algorithm robust to noise and varying density are combined to extract effective local shape descriptors. Structural components with physically meaningful labels are generated via structural labelling and clustering. During the classification stage, we consider the structural information at various scales and locations and encode it into a conditional random-field model for unary and pairwise inferences. High-order potentials are also introduced into the conditional random field to eliminate regional label noise. These high-order potentials are defined upon regions independent of connection relationships and can therefore take effect on isolated nodes. Experiments with two MLS datasets of typical urban scenes in Paris and Hong Kong were used to evaluate the performance of the proposed method. Nine and eleven different object classes were recognized from these two datasets with overall accuracies of 97.13% and 95.79%, respectively, indicating the effectiveness of the proposed method of interpreting complex urban scenes from point clouds with large variations in point density. Compared with previous studies on the Paris dataset, our method was able to recognize more classes and obtained a mean F1-score of 72.70% of seven common classes, being higher than the best of previous results. Numéro de notice : A2019-262 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.05.007 date de publication en ligne : 28/05/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.05.007 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93075 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019071	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2019073	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2019072	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Automatic building rooftop extraction from aerial images via hierarchical RGB-D priors / Shibiao Xu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)  

Permalink

Toward evaluating multiscale segmentations of high spatial resolution remote sensing images / Xueliang Zhang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 7 (July 2015)

Permalink

Object-based hyperspectral classification of urban areas using marker-based hierarchical segmentation / Davood Akbari in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 10 (October 2014)  

Permalink

Approches multi-hiérarchiques pour l'analyse d'images de télédétection / Camille Kurtz in Revue Française de Photogrammétrie et de Télédétection, n° 205 (Janvier 2014)

Permalink

Fast hierarchical segmentation of high-resolution remote sensing images with adaptative edge penalty / Xuellang Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 1 (January 2014)  

Permalink

Hierarchical segmentation-based software for cover classification analyses of seabed images (Seascape) / Nuria Teixido in Marine Ecology Progress Series (MEPS), n° 431 ([09/06/2011])    

Permalink

Stéréovision par zone outils et structure d’un système expert / Yannick Remion (1988)

Permalink