Centre dedocumentation
scientifique

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)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 154 (August 2019) . - pp 246 - 258 Titre : Pyramid scene parsing network in 3D: Improving semantic segmentation of point clouds with multi-scale contextual information Type de document : Article/Communication Auteurs : Hao Fang, Auteur ; Florent Lafarge, Auteur Année de publication : 2019 Article en page(s) : pp 246 - 258 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] prise en compte du contexte [Termes descripteurs IGN] représentation multiple [Termes descripteurs IGN] scène [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] semis de points Résumé : (Auteur) Analyzing and extracting geometric features from 3D data is a fundamental step in 3D scene understanding. Recent works demonstrated that deep learning architectures can operate directly on raw point clouds, i.e. without the use of intermediate grid-like structures. These architectures are however not designed to encode contextual information in-between objects efficiently. Inspired by a global feature aggregation algorithm designed for images (Zhao et al., 2017), we propose a 3D pyramid module to enrich pointwise features with multi-scale contextual information. Our module can be easily coupled with 3D semantic segmentation methods operating on 3D point clouds. We evaluated our method on three large scale datasets with four baseline models. Experimental results show that the use of enriched features brings significant improvements to the semantic segmentation of indoor and outdoor scenes. Numéro de notice : A2019-271 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.06.010 date de publication en ligne : 01/07/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.06.010 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93089 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019081	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019083	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019082	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Geometric camera pose refinement with learned depth maps / Nathan Piasco (2019)  

Public Titre : Geometric camera pose refinement with learned depth maps Type de document : Article/Communication Auteurs : Nathan Piasco , Auteur ; Désiré Sidibé, Auteur ; Cédric Demonceaux, Auteur ; Valérie Gouet-Brunet , Auteur Congrès : ICIP 2019, 26th IEEE International Conference on Image Processing (22 - 25 septembre 2019; Taipei, Taiwan), Commanditaire Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN Année de publication : 2019 Autre Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Projets : PLaTINUM / Gouet-Brunet, Valérie Importance : 5 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme ICP [Termes descripteurs IGN] carte de profondeur [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] semis de points Résumé : (auteur) We present a new method for image-only camera relocalisation composed of a fast image indexing retrieval step followed by pose refinement based on ICP (Iterative Closest Point). The first step aims to find an initial pose for the query by evaluating images similarity with low dimensional global deep descriptors. Subsequently, we predict with a fully convolutional deep encoder-decoder neural network a dense depth map from the image query. We use this depth map to create a local point cloud and refine the initial query pose using an ICP algorithm.We demonstrate the effectiveness of our new approach on various indoor scenes. Compared to learned pose regression methods, our proposal can be used on multiple scenes without the need of a specific weights-setup for each scene, while showing equivalent results. Numéro de notice : C2019-015 Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/ICIP.2019.8803014 date de publication en ligne : 26/08/2019 En ligne : https://doi.org/10.1109/ICIP.2019.8803014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93279

Configurable 3D scene synthesis and 2D image rendering with per-pixel ground truth using stochastic grammars / Chenfanfu Jiang in International journal of computer vision, vol 126 n° 9 (September 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 9 (September 2018) . - pp 920 - 941 Titre : Configurable 3D scene synthesis and 2D image rendering with per-pixel ground truth using stochastic grammars Type de document : Article/Communication Auteurs : Chenfanfu Jiang, Auteur ; Shuyao Qi, Auteur ; Yixin Zhu, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 920 - 941 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] architecture pipeline [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] reconstruction automatique [Termes descripteurs IGN] rendu réaliste [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] synthèse d'image Résumé : (Auteur) We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks—depth and surface normal prediction, semantic segmentation, reconstruction, etc.—and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner. Numéro de notice : A2018-416 Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1103-5 date de publication en ligne : 30/06/2018 En ligne : https://doi.org/10.1007/s11263-018-1103-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90899 [article]

Learning aggregated features and optimizing model for semantic labeling / Jianhua Wang in The Visual Computer, vol 33 n° 12 (December 2017)  

Public [article]  inThe Visual Computer > vol 33 n° 12 (December 2017) . - pp 1587 - 1600 Titre : Learning aggregated features and optimizing model for semantic labeling Type de document : Article/Communication Auteurs : Jianhua Wang, Auteur ; Chuanxia Zheng, Auteur ; Weihai Chen, Auteur ; Xingming Wu, Auteur Année de publication : 2017 Article en page(s) : pp 1587 - 1600 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] attribut [Termes descripteurs IGN] champ aléatoire conditionnel [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] modèle statistique [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] segmentation d'image Résumé : (Auteur) Semantic labeling for indoor scenes has been extensively developed with the wide availability of affordable RGB-D sensors. However, it is still a challenging task for multi-class recognition, especially for “small” objects. In this paper, a novel semantic labeling model based on aggregated features and contextual information is proposed. Given an RGB-D image, the proposed model first creates a hierarchical segmentation using an adapted gPb/UCM algorithm. Then, a support vector machine is trained to predict initial labels using aggregated features, which fuse small-scale appearance features, mid-scale geometric features, and large-scale scene features. Finally, a joint multi-label Conditional random field model that exploits both spatial and attributive contextual relations is constructed to optimize the initial semantic and attributive predicted results. The experimental results on the public NYU v2 dataset demonstrate the proposed model outperforms the existing state-of-the-art methods on the challenging 40 dominant classes task, and the model also achieves a good performance on a recent SUN RGB-D dataset. Especially, the prediction accuracy of “small” classes has been improved significantly. Numéro de notice : A2017-714 Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s00371-016-1302-4 En ligne : https://doi.org/10.1007/s00371-016-1302-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88098 [article]

Salient object detection in complex scenes via D-S evidence theory based region classification / Chunlei Yang in The Visual Computer, vol 33 n° 11 (November 2017)  

Public [article]  inThe Visual Computer > vol 33 n° 11 (November 2017) . - pp 1415 - 1428 Titre : Salient object detection in complex scenes via D-S evidence theory based region classification Type de document : Article/Communication Auteurs : Chunlei Yang, Auteur ; Jiexin Pu, Auteur ; Yongsheng Dong, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 1415 - 1428 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] fusion de données [Termes descripteurs IGN] information complexe [Termes descripteurs IGN] régionalisation [Termes descripteurs IGN] scène intérieure [Termes descripteurs IGN] théorie de Dempster-Shafer [Termes descripteurs IGN] zone saillante 3D Résumé : (Auteur) In complex scenes, multiple objects are often concealed in cluttered backgrounds. Their saliency is difficult to be detected by using conventional methods, mainly because single color contrast can not shoulder the mission of saliency measure; other image features should be involved in saliency detection to obtain more accurate results. Using Dempster-Shafer (D-S) evidence theory based region classification, a novel method is presented in this paper. In the proposed framework, depth feature information extracted from a coarse map is employed to generate initial feature evidences which indicate the probabilities of regions belonging to foreground or background. Based on the D-S evidence theory, both uncertainty and imprecision are modeled, and the conflicts between different feature evidences are properly resolved. Moreover, the method can automatically determine the mass functions of the two-stage evidence fusion for region classification. According to the classification result and region relevance, a more precise saliency map can then be generated by manifold ranking. To further improve the detection results, a guided filter is utilized to optimize the saliency map. Both qualitative and quantitative evaluations on three publicly challenging benchmark datasets demonstrate that the proposed method outperforms the contrast state-of-the-art methods, especially for detection in complex scenes. Numéro de notice : A2017-713 Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s00371-016-1288-y En ligne : https://doi.org/10.1007/s00371-016-1288-y Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88094 [article]

Bayesian graph-cut optimization for wall surfaces reconstruction in indoor environments / Georgios-Tsampikos Michailidis in The Visual Computer, vol 33 n° 10 (October 2017)  

Permalink

Viewing planning for range acquisition in indoor environments / Kok-Lim Low (2006) 

Permalink