Centre dedocumentation
scientifique

Learning and adapting robust features for satellite image segmentation on heterogeneous data sets / Sina Ghassemi in IEEE Transactions on geoscience and remote sensing, vol 57 n° 9 (September 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 9 (September 2019) . - pp 6517 - 6529 Titre : Learning and adapting robust features for satellite image segmentation on heterogeneous data sets Type de document : Article/Communication Auteurs : Sina Ghassemi, Auteur ; Attilio Friandrotti, Auteur ; Gianluca Francini, Auteur ; Enrico Magli, Auteur Année de publication : 2019 Article en page(s) : pp 6517 - 6529 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] chaîne de traitement [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] coût [Termes descripteurs IGN] données hétérogènes [Termes descripteurs IGN] image satellite [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] test de performance Résumé : (auteur) This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder–decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers’ statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. Numéro de notice : A2019-341 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2906689 date de publication en ligne : 17/04/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2906689 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93379 [article]

Spatially-explicit sensitivity and uncertainty analysis in a MCDA-based flood vulnerability model / Mariana Madruga de bruto in International journal of geographical information science IJGIS, vol 33 n° 9 (September 2019)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 33 n° 9 (September 2019) . - pp 1788-1806 Titre : Spatially-explicit sensitivity and uncertainty analysis in a MCDA-based flood vulnerability model Type de document : Article/Communication Auteurs : Mariana Madruga de bruto, Auteur ; Adrian Almoradie, Auteur ; Mariele Evers, Auteur Année de publication : 2019 Article en page(s) : pp 1788-1806 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse de sensibilité [Termes descripteurs IGN] analyse multicritère [Termes descripteurs IGN] Brésil [Termes descripteurs IGN] Geospatial data abstraction library [Termes descripteurs IGN] incertitude des données [Termes descripteurs IGN] inondation [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] processus d'analyse hiérarchisée [Termes descripteurs IGN] Python (langage de programmation) [Termes descripteurs IGN] vulnérabilité [Termes descripteurs IGN] zone à risque Résumé : (auteur) This study presents a methodology for conducting sensitivity and uncertainty analysis of a GIS-based multi-criteria model used to assess flood vulnerability in a case study in Brazil. The paper explores the robustness of model outcomes against slight changes in criteria weights. One criterion was varied at-a-time, while others were fixed to their baseline values. An algorithm was developed using Python and a geospatial data abstraction library to automate the variation of weights, implement the ANP (analytic network process) tool, reclassify the raster results, compute the class switches, and generate an uncertainty surface. Results helped to identify highly vulnerable areas that are burdened by high uncertainty and to investigate which criteria contribute to this uncertainty. Overall, the criteria ‘houses with improper building material’ and ‘evacuation drills and training’ are the most sensitive ones, thus, requiring more accurate measurements. The sensitivity of these criteria is explained by their weights in the base run, their spatial distribution, and the spatial resolution. These findings can support decision makers to characterize, report, and mitigate uncertainty in vulnerability assessment. The case study results demonstrate that the developed approach is simple, flexible, transparent, and may be applied to other complex spatial problems. Numéro de notice : A2019-389 Thématique : GEOMATIQUE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1599125 date de publication en ligne : 05/04/2019 En ligne : https://doi.org/10.1080/13658816.2019.1599125 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93480 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2019071	SL	Revue	Centre de documentation	Revues en salle	Disponible
079-2019072	SL	Revue	Centre de documentation	Revues en salle	Disponible

Robust M–M unscented Kalman filtering for GPS/IMU navigation / Cheng Yang in Journal of geodesy, vol 93 n° 8 (August 2019)  

Public [article]  inJournal of geodesy > vol 93 n° 8 (August 2019) . - pp 1093 - 1104 Titre : Robust M–M unscented Kalman filtering for GPS/IMU navigation Type de document : Article/Communication Auteurs : Cheng Yang, Auteur ; Wenzhong Shi, Auteur ; Wu Chen, Auteur Année de publication : 2019 Article en page(s) : pp 1093 - 1104 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes descripteurs IGN] coefficient de corrélation [Termes descripteurs IGN] erreur de mesure [Termes descripteurs IGN] erreur de modèle [Termes descripteurs IGN] filtre de Kalman [Termes descripteurs IGN] GNSS-INS [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] méthode du maximum de vraisemblance (estimation) [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] modèle non linéaire Résumé : (auteur) In this paper, a robust unscented Kalman filter (UKF) based on the generalized maximum likelihood estimation (M-estimation) is proposed to improve the robustness of the integrated navigation system of Global Navigation Satellite System and Inertial Measurement Unit. The UKF is a variation of Kalman filter by which the Jacobian matrix calculation in a nonlinear system state model is not necessary. The proposed robust M–M unscented Kalman filter (RMUKF) applies the M-estimation principle to both functional model errors and measurement errors. Hence, this robust filter attenuates the influences of disturbances in the dynamic model and of measurement outliers without linearizing the nonlinear state space model. In addition, an equivalent weight matrix, composed of the bi-factor shrink elements, is proposed in order to keep the original correlation coefficients of the predicted state unchanged. Furthermore, a nonlinear error model is used as the dynamic equation to verify the performance of the proposed RMUKF with a simulation and field test. Compared with the conventional UKF, the impacts of measurement outliers and system disturbances on the state estimation are both controlled by RMUKF. Numéro de notice : A2019-370 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-018-01227-5 date de publication en ligne : 22/01/2019 En ligne : https://doi.org/10.1007/s00190-018-01227-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93455 [article]

Demonstrating the transferability of forest inventory attribute models derived using airborne laser scanning data / Piotr Tompalski in Remote sensing of environment, vol 227 (15 June 2019)  

Public [article]  inRemote sensing of environment > vol 227 (15 June 2019) . - pp 110 - 124 Titre : Demonstrating the transferability of forest inventory attribute models derived using airborne laser scanning data Type de document : Article/Communication Auteurs : Piotr Tompalski, Auteur ; Joanne C. White, Auteur ; Nicholas C. Coops, Auteur ; Michael A. Wulder, Auteur Année de publication : 2019 Article en page(s) : pp 110 - 124 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] densité des points [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] méthode des moindres carrés [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] modèle mathématique [Termes descripteurs IGN] régression [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Airborne laser scanning (ALS) is a reliable source of accurate information for forest stand inventory attributes including height, cover, basal area, and volume. The commonly applied area-based approach (ABA) allows the derivation of wall-to-wall geospatial coverages representing each of the modeled attributes at a grid-cell level, with spatial resolutions typically between 20 and 30 m. The ABA predictive models are developed using stratified inventory data from field plots, the requirement for which can increase the overall cost of the ALS-based inventory. Parsimonious use of ground plots is a key means to control variable costs in the operational implementation of the ABA. In this paper, we demonstrate how the prediction accuracy of Lorey's height (HL, m), quadratic mean diameter (QMD, cm), and gross volume (V, m3) vary when existing ABA models are transferred to different areas or are applied to point cloud data with different characteristics than those on which the original model was developed. Specifically, we consider three scenarios of model transferability: (i) same point cloud characteristics, different areas; (ii) different point cloud characteristics, same areas; and (iii) different point cloud characteristics, different areas. We generated area-based models using three modeling approaches: linear regression (OLS), random forests (RF), and k-nearest neighbour (kNN) imputation. Results indicated that the prediction accuracy of area-based models varied by attribute and by modeling approach. We found that when the models were transferred their prediction accuracy decreased, with an average increase in relative bias up to 22.04%, and increase in relative RMSE up to 29.31%. Prediction accuracies for HL were higher than those of QMD or V when models were transferred, and had the lowest average increase in relative bias and relative RMSE of Numéro de notice : A2019-227 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2019.04.006 date de publication en ligne : 13/04/2019 En ligne : https://doi.org/10.1016/j.rse.2019.04.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92741 [article]

A breakpoint detection in the mean model with heterogeneous variance on fixed time-intervals / Olivier Bock in Statistics and Computing, vol 29 Online First (May 2019)  

Public [article]  inStatistics and Computing > vol 29 Online First (May 2019) . - pp 1 - 13 Titre : A breakpoint detection in the mean model with heterogeneous variance on fixed time-intervals Type de document : Article/Communication Auteurs : Olivier Bock , Auteur ; Xavier Collilieux , Auteur ; François Guillamon, Auteur ; Emilie Lebarbier, Auteur ; Claire Pascal, Auteur Année de publication : 2019 Projets : 1-Pas de projet / Article en page(s) : pp 1 - 13 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes descripteurs IGN] analyse de variance [Termes descripteurs IGN] données GNSS [Termes descripteurs IGN] inférence statistique [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] points de rupture [Termes descripteurs IGN] processus gaussien [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] variabilité Résumé : (Auteur) This work is motivated by an application for the homogenization of global navigation satellite system (GNSS)-derived integrated water vapour series. Indeed, these series are affected by abrupt changes due to equipment changes or environmental effects. The detection and correction of the series from these changes are a crucial step before any use for climate studies. In addition to these abrupt changes, it has been observed in the series a non-stationary of the variability. We propose in this paper a new segmentation model that is a breakpoint detection in the mean model of a Gaussian process with heterogeneous variance on known time intervals. In this segmentation case, the dynamic programming algorithm used classically to infer the breakpoints cannot be applied anymore. We propose a procedure in two steps: we first estimate robustly the variances and then apply the classical inference by plugging these estimators. The performance of our proposed procedure is assessed through simulation experiments. An application to real GNSS data is presented. Numéro de notice : A2019-165 Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11222-019-09853-5 date de publication en ligne : 03/05/2019 En ligne : https://doi.org/10.1007/s11222-019-09853-5 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92571 [article]

Coastline extraction from SAR images using robust ridge tracing / Dailiang Wang in Marine geodesy, vol 42 n° 3 (May 2019)  

Permalink

A derivative-free optimization-based approach for detecting architectural symmetries from 3D point clouds / Fan Xue in ISPRS Journal of photogrammetry and remote sensing, vol 148 (February 2019)  

Permalink

Robust vehicle detection in aerial images using bag-of-words and orientation aware scanning / Hailing Zhou in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)  

Permalink

Adaptive correlation filters with long-term and short-term memory for object tracking / Chao Ma in International journal of computer vision, vol 126 n° 8 (August 2018)  

Permalink

A deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification / Zhen Wang in IEEE Transactions on geoscience and remote sensing, vol 56 n° 8 (August 2018)  

Permalink

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)  

Permalink

Label propagation with ensemble of pairwise geometric relations : towards robust large-scale retrieval of object instances / Xiaomeng Wu in International journal of computer vision, vol 126 n° 7 (July 2018)  

Permalink

The efficiency of different outlier detection approaches in geodetic networks: case study for Pobednik statue / Mehmed Batilović in Geodetski vestnik, vol 62 n° 2 (June 2018)  

Permalink

Crowdsourcing the character of a place : Character‐level convolutional networks for multilingual geographic text classification / Benjamin Adams in Transactions in GIS, vol 22 n° 2 (April 2018)  

Permalink

Real-time accurate 3D head tracking and pose estimation with consumer RGB-D cameras / David Joseph Tan in International journal of computer vision, vol 126 n° 2-4 (April 2018)  

Permalink