Centre de documentation
scientifique

A lightweight network with attention decoder for real-time semantic segmentation / Kang Wang in The Visual Computer, vol 38 n° 7 (July 2022)  

Public [article]  inThe Visual Computer > vol 38 n° 7 (July 2022) . - pp 2329 - 2339 Titre : A lightweight network with attention decoder for real-time semantic segmentation Type de document : Article/Communication Auteurs : Kang Wang, Auteur ; Jinfu Yang, Auteur ; Shuai Yuan, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2329 - 2339 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] attention (apprentissage automatique) [Termes IGN] jeu de données [Termes IGN] précision [Termes IGN] segmentation sémantique [Termes IGN] temps réel [Termes IGN] vitesse de traitement Résumé : (auteur) As an important task in scene understanding, semantic segmentation requires a large amount of computation to achieve high performance. In recent years, with the rise of autonomous systems, it is crucial to make a trade-off in terms of accuracy and speed. In this paper, we propose a novel asymmetric encoder–decoder network structure to address this problem. In the encoder, we design a Separable Asymmetric Module, which combines depth-wise separable asymmetric convolution with dilated convolution to greatly reduce computation cost while maintaining accuracy. On the other hand, an attention mechanism is also used in the decoder to further improve segmentation performance. Experimental results on CityScapes and CamVid datasets show that the proposed method can achieve a better balance between segmentation precision and speed compared with state-of-the-art semantic segmentation methods. Specifically, our model obtains mean IoU of 72.5% and 66.3% on CityScapes and CamVid test dataset, respectively, with less than 1M parameters. Numéro de notice : A2022-508 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-021-02115-4 Date de publication en ligne : 07/05/2021 En ligne : https://doi.org/10.1007/s00371-021-02115-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101041 [article]

Dater les documents cartographiques / Jean-Luc Arnaud in e-Perimetron, vol 17 n° 1 (avril 2022)  

Public [article]  ine-Perimetron > vol 17 n° 1 (avril 2022) . - pp 1 - 18 Titre : Dater les documents cartographiques Type de document : Article/Communication Auteurs : Jean-Luc Arnaud, Auteur Année de publication : 2022 Article en page(s) : pp 1 - 18 Note générale : bibliographie Langues : Français (fre) Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie ancienne [Termes IGN] cartographie militaire [Termes IGN] datation [Termes IGN] dépôt de la guerre [Termes IGN] document cartographique [Termes IGN] échelle cartographique [Termes IGN] édition cartographique [Termes IGN] histoire [Termes IGN] précision [Termes IGN] Service Géographique de l'Armée [Termes IGN] utilisateur Résumé : (auteur) Cet article examine les modes de datation de la production cartographique française depuis la fin du XVIIIe siècle. Il est composé de sept chapitres thématiques qui envisagent la multiplicité des pratiques des éditeurs et montrent qu’en fonction de l’usage envisagé pour chaque document et de son niveau de précision, les enjeux portés par la datation prennent des formes différentes. Numéro de notice : A2022-294 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : sans En ligne : http://www.e-perimetron.org/Vol_17_1/Arnaud.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100346 [article]

PpC: a new method to reduce the density of lidar data. Does it affect the DEM accuracy? / Sandra Bujan in Photogrammetric record, vol 34 n° 167 (September 2019)  

Public [article]  inPhotogrammetric record > vol 34 n° 167 (September 2019) . - pp Titre : PpC: a new method to reduce the density of lidar data. Does it affect the DEM accuracy? Type de document : Article/Communication Auteurs : Sandra Bujan, Auteur ; Edouardo M. González‐Ferreiro, Auteur ; Miguel Cordero, Auteur ; David Miranda, Auteur Année de publication : 2019 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] densité des points [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] échantillonnage [Termes IGN] modèle numérique de surface [Termes IGN] pente [Termes IGN] précision [Termes IGN] R (langage) [Termes IGN] réduction Résumé : (auteur) In cost–benefit analysis of lidar data acquisition, point density is often artificially reduced in order to examine how this affects the quality of derived products. However, the performance of the different density reduction methods has not yet been compared and their influence on the accuracy of the models and results has not been evaluated. A novel method for reducing the point density, termed Proportional per Cell (PpC), is presented and compared with the performance of three other reduction methods, examining their influence on the accuracy of lidar‐derived digital surface models using ISPRS reference data. The results indicate that the PpC method was better at conserving the characteristics of the original data. However, point density, sample type and slope had a greater influence than the reduction method used. Numéro de notice : A2019-499 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/phor.12295 Date de publication en ligne : 10/10/2019 En ligne : https://doi.org/10.1111/phor.12295 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93763 [article]

The Naïve Overfitting Index Selection (NOIS): A new method to optimize model complexity for hyperspectral data / Alby D. Rocha in ISPRS Journal of photogrammetry and remote sensing, vol 133 (November 2017)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 133 (November 2017) . - pp 61 - 74 Titre : The Naïve Overfitting Index Selection (NOIS): A new method to optimize model complexity for hyperspectral data Type de document : Article/Communication Auteurs : Alby D. Rocha, Auteur ; Thomas A. Groen, Auteur ; Andrew K. Skidmore, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 61 - 74 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] complexité [Termes IGN] image hyperspectrale [Termes IGN] méthode robuste [Termes IGN] modèle de simulation [Termes IGN] optimisation (mathématiques) [Termes IGN] précision [Termes IGN] régression [Termes IGN] validation des données Résumé : (Auteur) The growing number of narrow spectral bands in hyperspectral remote sensing improves the capacity to describe and predict biological processes in ecosystems. But it also poses a challenge to fit empirical models based on such high dimensional data, which often contain correlated and noisy predictors. As sample sizes, to train and validate empirical models, seem not to be increasing at the same rate, overfitting has become a serious concern. Overly complex models lead to overfitting by capturing more than the underlying relationship, and also through fitting random noise in the data. Many regression techniques claim to overcome these problems by using different strategies to constrain complexity, such as limiting the number of terms in the model, by creating latent variables or by shrinking parameter coefficients. This paper is proposing a new method, named Naïve Overfitting Index Selection (NOIS), which makes use of artificially generated spectra, to quantify the relative model overfitting and to select an optimal model complexity supported by the data. The robustness of this new method is assessed by comparing it to a traditional model selection based on cross-validation. The optimal model complexity is determined for seven different regression techniques, such as partial least squares regression, support vector machine, artificial neural network and tree-based regressions using five hyperspectral datasets. The NOIS method selects less complex models, which present accuracies similar to the cross-validation method. The NOIS method reduces the chance of overfitting, thereby avoiding models that present accurate predictions that are only valid for the data used, and too complex to make inferences about the underlying process. Numéro de notice : A2017-722 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.09.012 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.09.012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88407 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2017111	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2017112	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt
081-2017113	DEP-EXM	Revue	Saint-Mandé	Dépôt en unité	Exclu du prêt

On the computation of reliable formal uncertainties in the densification of GPS-levelling networks by least-squares collocation / E. Mysen in Journal of geodesy, vol 88 n° 10 (October 2014)  

Public [article]  inJournal of geodesy > vol 88 n° 10 (October 2014) . - pp 917 - 926 Titre : On the computation of reliable formal uncertainties in the densification of GPS-levelling networks by least-squares collocation Type de document : Article/Communication Auteurs : E. Mysen, Auteur Année de publication : 2014 Article en page(s) : pp 917 - 926 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Nivellement [Termes IGN] collocation par moindres carrés [Termes IGN] optimisation (mathématiques) [Termes IGN] précision Résumé : (Auteur) A realization of a height system covering the south of Norway has been performed, based on least-squares collocation applied to differences between geometric and gravimetric quasigeoid heights, inhomogeneous and isotropic covariance modelling, and without prior information on the error sources of the involved data types. As a result, the derived normal heights were biased by the systematic errors of the GPS-levelling network. The important covariance properties were determined at every location from spatially differenced observations, and made it straightforward to evaluate the uncertainties of the biased height reference. The distribution of predictions followed a Gaussian shape, but extreme realizations were overrepresented. Numéro de notice : A2014-514 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-014-0732-x Date de publication en ligne : 01/06/2014 En ligne : https://doi.org/10.1007/s00190-014-0732-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74118 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
266-2014101	SL	Revue	Centre de documentation	Revues en salle	Disponible

IGS-MGEX, on prépare le terrain pour les sciences et techniques GNSS multi-constellation / Oliver Montenbruck in XYZ, n° 140 (septembre - novembre 2014) 

Permalink

GNSS solutions: quantifying the performance of navigation systems and standards for assisted-GNSS / Sam Pullen in Inside GNSS, vol 3 n° 6 (September 2008) 

Permalink

Un SIG qui mange du lion / Anonyme in Géomatique expert, n° 39 (01/12/2004)

Permalink

SMEX02: field scale variability, time stability and similarity of soil moisture / J.M. Jacobs in Remote sensing of environment, vol 92 n° 4 (30 September 2004)  

Permalink

Protection of geoprivacy and accuracy of spatial information: how effective are geographical masks ? / Mei-Po Kwan in Cartographica, vol 39 n° 2 (June 2004)  

Permalink

Real-time kinematic in the light of GPS modernisation and Galileo / B. Eisfeller in Galileo's world, vol 4 n° 2 (01/09/2002)

Permalink

Evaluation of SAR-optical imagery synthesis techniques in a complex coastal ecosystem / F.M. Henderson in Photogrammetric Engineering & Remote Sensing, PERS, vol 68 n° 8 (August 2002)  

Permalink

Effects of JPEG compression on the accuracy of digital terrain models automatically derived from digital aerial images / K.W. Lam in Photogrammetric record, vol 17 n° 98 (October 2001 - March 2002)  

Permalink

Uncertain topological relations between imprecise regions / Stephan Winter in International journal of geographical information science IJGIS, vol 14 n° 5 (july 2000)  

Permalink

Compression et précision : les deux axes du traitement d'images / Anonyme in Géomatique expert, n° 6 (01/06/2000)

Permalink