Centre dedocumentation
scientifique

Representing shape collections with alignment-aware linear models / Romain Loiseau (2021)  

Public Titre : Representing shape collections with alignment-aware linear models Type de document : Article/Communication Auteurs : Romain Loiseau, Auteur ; Tom Monnier, Auteur ; Loïc Landrieu , Auteur ; Mathieu Aubry, Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2021 Projets : READY3D / Landrieu, Loïc Importance : 17 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de données [Termes IGN] apprentissage profond [Termes IGN] données localisées 3D [Termes IGN] modèle linéaire [Termes IGN] réseau neuronal profond [Termes IGN] segmentation [Termes IGN] semis de points [Termes IGN] transformation affine Résumé : (auteur) In this paper, we revisit the classical representation of 3D point clouds as linear shape models. Our key insight is to leverage deep learning to represent a collection of shapes as affine transformations of low-dimensional linear shape models. Each linear model is characterized by a shape prototype, a low-dimensional shape basis and two neural networks. The networks take as input a point cloud and predict the coordinates of a shape in the linear basis and the affine transformation which best approximate the input. Both linear models and neural networks are learned end-to-end using a single reconstruction loss. The main advantage of our approach is that, in contrast to many recent deep approaches which learn feature-based complex shape representations, our model is explicit and every operation occurs in 3D space. As a result, our linear shape models can be easily visualized and annotated, and failure cases can be visually understood. While our main goal is to introduce a compact and interpretable representation of shape collections, we show it leads to state of the art results for few-shot segmentation. Code and data are available at: https://romainloiseau.github.io/deep-linear-shapes Numéro de notice : P2021-005 Affiliation des auteurs : UGE-LaSTIG+Ext (2020- ) Thématique : INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : sans date de publication en ligne : 03/09/2021 En ligne : https://arxiv.org/abs/2109.01605 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98385

A bevy of area-preserving transforms for map projection designers / Daniel "daan" Strebe in Cartography and Geographic Information Science, vol 46 n° 3 (May 2019)  

Public [article]  inCartography and Geographic Information Science > vol 46 n° 3 (May 2019) . - pp 260 - 276 Titre : A bevy of area-preserving transforms for map projection designers Type de document : Article/Communication Auteurs : Daniel "daan" Strebe, Auteur Année de publication : 2019 Article en page(s) : pp 260 - 276 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Projections [Termes IGN] projection [Termes IGN] projection Aitoff [Termes IGN] projection de Bonne [Termes IGN] projection de Hammer-Aitoff [Termes IGN] projection équivalente [Termes IGN] transformation affine [Termes IGN] transformation de coordonnées [Termes IGN] web mapping Résumé : (Auteur) Sometimes map projection designers need to create equal-area projections to best fill the projections’ purposes. However, unlike for conformal projections, few transformations have been described that can be applied to equal-area projections to develop new equal-area projections. Here, I survey area-preserving transformations, giving examples of their applications and proposing an efficient way of deploying an equal-area system for raster-based Web mapping. Together, these transformations provide a toolbox for the map projection designer working in the area-preserving domain. Numéro de notice : A2019-094 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2018.1452632 date de publication en ligne : 05/04/2018 En ligne : https://doi.org/10.1080/15230406.2018.1452632 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92342 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2019031	SL	Revue	Centre de documentation	Revues en salle	Disponible

Least squares support vector machine model for coordinate transformation / Yao Yevenyo Ziggah in Geodesy and cartography, vol 45 n° 1 (2019)  

Public [article]  inGeodesy and cartography > vol 45 n° 1 (2019) . - pp 16 - 27 Titre : Least squares support vector machine model for coordinate transformation Type de document : Article/Communication Auteurs : Yao Yevenyo Ziggah, Auteur Année de publication : 2019 Article en page(s) : pp 16 - 27 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux [Termes IGN] Ghana [Termes IGN] méthode des moindres carrés [Termes IGN] projection conforme [Termes IGN] résidu [Termes IGN] séparateur à vaste marge [Termes IGN] transformation affine [Termes IGN] transformation de coordonnées Résumé : (auteur) In coordinate transformation, the main purpose is to provide a mathematical relationship between coordinates related to different geodetic reference frames. This gives the geospatial professionals the opportunity to link different datums together. Review of previous studies indicates that empirical and soft computing models have been proposed in recent times for coordinate transformation. The main aim of this study is to present the applicability and performance of Least Squares Support Vector Machine (LS-SVM) which is an extension of the Support Vector Machine (SVM) for coordinate transformation. For comparison purpose, the SVM and the widely used Backpropagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN), 2D conformal and affine methods were also employed. To assess how well the transformation results fit the observed data, the root mean square of the residual horizontal distances and standard deviation were used. From the results obtained, the LS-SVM and RBFNN had comparable results and were better than the other methods. The overall statistical findings produced by LS-SVM met the accuracy requirement for cadastral surveying applications in Ghana. To this end, the proposed LS-SVM is known to possess promising predictive capabilities and could efficiently be used as a supplementary technique for coordinate transformation. Numéro de notice : A2019-482 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.3846/gac.2019.6053 date de publication en ligne : 17/04/2019 En ligne : https://doi.org/10.3846/gac.2019.6053 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93629 [article]

Robust detection and affine rectification of planar homogeneous texture for scene understanding / Shahzor Ahmad in International journal of computer vision, vol 126 n° 8 (August 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 8 (August 2018) . - pp 822 - 854 Titre : Robust detection and affine rectification of planar homogeneous texture for scene understanding Type de document : Article/Communication Auteurs : Shahzor Ahmad, Auteur ; Loong-Fah Cheong, Auteur Année de publication : 2018 Article en page(s) : pp 822 - 854 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] compréhension de l'image [Termes IGN] méthode robuste [Termes IGN] scène [Termes IGN] texture d'image [Termes IGN] transformation affine Résumé : (Auteur) Man-made environments tend to be abundant with planar homogeneous texture, which manifests as regularly repeating scene elements along a plane. In this work, we propose to exploit such structure to facilitate high-level scene understanding. By robustly fitting a texture projection model to optimal dominant frequency estimates in image patches, we arrive at a projective-invariant method to localize such generic, semantically meaningful regions in multi-planar scenes. The recovered projective parameters also allow an affine-ambiguous rectification in real-world images marred with outliers, room clutter, and photometric severities. Comprehensive qualitative and quantitative evaluations are performed that show our method outperforms existing representative work for both rectification and detection. The potential of homogeneous texture for two scene understanding tasks is then explored. Firstly, in environments where vanishing points cannot be reliably detected, or the Manhattan assumption is not satisfied, homogeneous texture detected by the proposed approach is shown to provide alternative cues to obtain a scene geometric layout. Second, low-level feature descriptors extracted upon affine rectification of detected texture are found to be not only class-discriminative but also complementary to features without rectification, improving recognition performance on the 67-category MIT benchmark of indoor scenes. One of our configurations involving deep ConvNet features outperforms most current state-of-the-art work on this dataset, achieving a classification accuracy of 76.90%. The approach is additionally validated on a set of 31 categories (mostly outdoor man-made environments exhibiting regular, repeating structure), being a subset of the large-scale Places2 scene dataset. Numéro de notice : A2018-415 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1078-2 date de publication en ligne : 22/03/2018 En ligne : https://doi.org/10.1007/s11263-018-1078-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90898 [article]

The triangulated affine transformation parameters and barycentric coordinates of Turkish Permanent GPS Network / Kutubuddin Ansari in Survey review, vol 50 n° 362 (August 2018)  

Public [article]  inSurvey review > vol 50 n° 362 (August 2018) . - pp 412 - 415 Titre : The triangulated affine transformation parameters and barycentric coordinates of Turkish Permanent GPS Network Type de document : Article/Communication Auteurs : Kutubuddin Ansari, Auteur ; Ozsen Corumluoglu, Auteur ; Payal Verma, Auteur Année de publication : 2018 Article en page(s) : pp 412 - 415 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux [Termes IGN] barycentre [Termes IGN] Eurasia Fixed Reference Frame [Termes IGN] réseau géodésique permanent [Termes IGN] transformation affine [Termes IGN] transformation de coordonnées [Termes IGN] Turquie Résumé : (Auteur) There are several computational approaches and methods to produce the complete solutions of geometry problems and they give sufficient computational strength for geodetic networks. Every approach and method has their advantages and drawbacks. Barycentric coordinates, also called areal coordinates, provide a new knock approach for geometry problems of such networks. This coordinate system offers triangular finite elements which are quite different from the usual Cartesian coordinate system. Actually, barycentric coordinates are a natural system of coordinates for the affine geometry. The modified approach for the affine transformation and barycentric coordinate system has been introduced and discussed, respectively in the study whether the affine transformation improves the results deteriorated by geometry of a GPS network. For this aim, general affine transformation of six-parameters between Eurasia Fixed Reference Frame (EUREF) and International Terrestrial Reference Frame (ITRF) for Turkish Permanent Global Positioning System Network (TPGN) has been computed. The affine transformation results show that the effects of the first and second translation parameters are in negative and positive directions, respectively. The third and sixth parameters are almost constant, on the other hand the fourth and fifth have a very small positive effect. Additionally, three triangular networks of GPS stations, at different locations in Turkey as a numerical example of barycentric coordinates, have also been presented. In the numerical example, the coordinate values of EUREF and ITRF have some differences after the decimal point, but the barycentric coordinates have very small amount of differences (sixth digit after decimal) which proves that the modified approach is meaningful. Numéro de notice : A2018-447 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2017.1297016 date de publication en ligne : 05/03/2017 En ligne : https://doi.org/10.1080/00396265.2017.1297016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91032 [article]

4FP-structure: a robust local region feature descriptor / Jiayuan Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 12 (December 2017)  

Permalink

Nonlinear bias compensation of ZiYuan-3 satellite imagery with cubic splines / Jinshan Cao in ISPRS Journal of photogrammetry and remote sensing, vol 133 (November 2017)  

Permalink

Geometric accuracy evaluation of YG-18 satellite imagery based on RFM / Ruishan Zhao in Photogrammetric record, vol 32 n° 157 (March - May 2017)  

Permalink

Extendable linearised adjustment model for deformation analysis / Hiddo Velsink in Survey review, vol 47 n° 345 (November 2015)  

Permalink

An alternative method to constructing time cartograms for the visual representation of scheduled movement data / Rehmat Ullah in Journal of maps, vol 11 n° 4 ([01/08/2015])  

Permalink

Photogrammetric techniques for voxel-based flow velocity field measurement / Patrick Westfeld in Photogrammetric record, vol 26 n° 136 (December 2011 - February 2012)  

Permalink

Mathématiques pour la modélisation géométrique, la représentation 3D et la synthèse d'images / L. Garnier (2007)

Permalink