Centre dedocumentation
scientifique

Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network / Chunping Qiu 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 151 - 162 Titre : Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network Type de document : Article/Communication Auteurs : Chunping Qiu, Auteur ; Lichao Mou, Auteur ; Michael Schmitt, Auteur ; Xiao Xiang Zhu, Auteur Année de publication : 2019 Article en page(s) : pp 151 - 162 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] climat urbain [Termes descripteurs IGN] image multitemporelle [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] réseau neuronal récurrent [Termes descripteurs IGN] résidu [Termes descripteurs IGN] ville Résumé : (Auteur) The local climate zone (LCZ) scheme was originally proposed to provide an interdisciplinary taxonomy for urban heat island (UHI) studies. In recent years, the scheme has also become a starting point for the development of higher-level products, as the LCZ classes can help provide a generalized understanding of urban structures and land uses. LCZ mapping can therefore theoretically aid in fostering a better understanding of spatio-temporal dynamics of cities on a global scale. However, reliable LCZ maps are not yet available globally. As a first step toward automatic LCZ mapping, this work focuses on LCZ-derived land cover classification, using multi-seasonal Sentinel-2 images. We propose a recurrent residual network (Re-ResNet) architecture that is capable of learning a joint spectral-spatial-temporal feature representation within a unitized framework. To this end, a residual convolutional neural network (ResNet) and a recurrent neural network (RNN) are combined into one end-to-end architecture. The ResNet is able to learn rich spectral-spatial feature representations from single-seasonal imagery, while the RNN can effectively analyze temporal dependencies of multi-seasonal imagery. Cross validations were carried out on a diverse dataset covering seven distinct European cities, and a quantitative analysis of the experimental results revealed that the combined use of the multi-temporal information and Re-ResNet results in an improvement of approximately 7 percent points in overall accuracy. The proposed framework has the potential to produce consistent-quality urban land cover and LCZ maps on a large scale, to support scientific progress in fields such as urban geography and urban climatology. Numéro de notice : A2019-268 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.05.004 date de publication en ligne : 14/06/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.05.004 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93085 [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

Seasonal pattern in time series of variances of GPS residual errors Anova estimates / Darko Anđić in Geodetski vestnik, vol 63 n° 2 (June - August 2019)  

Public [article]  inGeodetski vestnik > vol 63 n° 2 (June - August 2019) . - pp 260 - 271 Titre : Seasonal pattern in time series of variances of GPS residual errors Anova estimates Type de document : Article/Communication Auteurs : Darko Anđić, Auteur Année de publication : 2019 Article en page(s) : pp 260 - 271 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes descripteurs IGN] double différence [Termes descripteurs IGN] positionnement par GPS [Termes descripteurs IGN] propagation ionosphérique [Termes descripteurs IGN] propagation troposphérique [Termes descripteurs IGN] rayonnement solaire [Termes descripteurs IGN] résidu [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] variance [Termes descripteurs IGN] variation saisonnière Résumé : (auteur) In this paper, which represents a continuation of the previous author's work, an inconstancy of GPS residual error ANOVA estimates and their variances are presented. For the purpose of the analysis, fixed solutions for all of the three coordinates, e (eastwards), n (northwards) and u (upwards), obtained by using ionosphere-free (L0) linear combination of double-difference phase observations in the processing of GPS data, were employed. The aim of the research was to consider the behaviour of variances of GPS residual error ANOVA estimates in time because there has not been any paper dealing with that issue so far. Herein, it turned out a seasonal pattern in related time series was present. In addition, it was concluded there was a difference in ANOVA estimate extreme values obtained when one considered daily data subsets compared to those obtained in the approach considering monthly data of the fixed solutions. GPS data collected at ending stations of a baseline of 40 km in length within a four-year period, involving the lowest and increased solar activity, were used in calculations. Numéro de notice : A2019-405 Thématique : POSITIONNEMENT Nature : Article DOI : 10.15292/geodetski-vestnik.2019.02.260-271 En ligne : http://dx.doi.org/10.15292/geodetski-vestnik.2019.02.260-271 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93509 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2019021	SL	Revue	Centre de documentation	Revues en salle	Disponible

An improved robust Kalman filtering strategy for GNSS kinematic positioning considering small cycle slips / Wanke Liu in Advances in space research, vol 63 n° 9 (1 May 2019)  

Public [article]  inAdvances in space research > vol 63 n° 9 (1 May 2019) . - pp 2724 - 2734 Titre : An improved robust Kalman filtering strategy for GNSS kinematic positioning considering small cycle slips Type de document : Article/Communication Auteurs : Wanke Liu, Auteur ; Jianlong Li, Auteur ; Qi Zeng, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 2724 - 2734 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes descripteurs IGN] erreur absolue [Termes descripteurs IGN] erreur de positionnement [Termes descripteurs IGN] filtre de Kalman [Termes descripteurs IGN] glissement de cycle [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] phase [Termes descripteurs IGN] positionnement cinématique [Termes descripteurs IGN] positionnement différentiel [Termes descripteurs IGN] positionnement par GNSS [Termes descripteurs IGN] résidu [Termes descripteurs IGN] valeur aberrante Résumé : (auteur) In GNSS (Global Navigation Satellite Systems) kinematic positioning, observations will be inevitably contaminated by cycle slips and gross errors, as the complex observation environment changes rapidly. These outliers will degrade the performance of classic Kalman filtering applied in GNSS kinematic resolution and eventually, the filtering may converge slowly or even diverge and thus the precision will be degraded. Therefore, a robust Kalman filter should be applied to resist the influence of these outliers that cannot be identified in the data preprocessing stage. Based on the conventional IGG (Institute of Geodesy and Geophysics) III equivalent weight method which addresses the outliers of the zero-weight segment with the same strategy, this paper proposes an improved robust Kalman filtering strategy that detects outliers by both posterior phase residuals and standardized residuals and handles the carrier-phase observation of zero-weight segment as cycle slips. In addition, to avoid unnecessary ambiguity reinitialization caused by the detected cycle slips, only when the carrier-phase observation of the same satellite is classified in the zero-weight segment over two consecutive epochs should the ambiguity be reinitialized. Experimental results of relative positioning show that the improved method can not only mitigate the influence of unexpected outliers in the Kalman filter but also improve the fixing rate of ambiguity resolution as well as the accuracy and reliability of positioning. Numéro de notice : A2019-396 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.asr.2017.11.041 date de publication en ligne : 08/12/2017 En ligne : https://doi.org/10.1016/j.asr.2017.11.041 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93505 [article]

Assessing the latest performance of Galileo-only PPP and the contribution of Galileo to Multi-GNSS PPP / Fengyu Xiu in Advances in space research, vol 63 n° 9 (1 May 2019)  

Public [article]  inAdvances in space research > vol 63 n° 9 (1 May 2019) . - pp 2784 - 2795 Titre : Assessing the latest performance of Galileo-only PPP and the contribution of Galileo to Multi-GNSS PPP Type de document : Article/Communication Auteurs : Fengyu Xiu, Auteur ; Shirong Ye, Auteur ; Pengfei Xia, Auteur ; Lewen Zhao, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 2784 - 2795 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] constellation Galileo [Termes descripteurs IGN] erreur systématique inter-systèmes [Termes descripteurs IGN] GalileoSat [Termes descripteurs IGN] positionnement cinématique [Termes descripteurs IGN] positionnement par Galileo [Termes descripteurs IGN] positionnement par GLONASS [Termes descripteurs IGN] positionnement par GPS [Termes descripteurs IGN] positionnement ponctuel précis [Termes descripteurs IGN] précision du positionnement [Termes descripteurs IGN] résidu [Termes descripteurs IGN] trajet multiple [Vedettes matières IGN] Traitement de données GNSS Résumé : (auteur) By the end of 2016, the Galileo constellation had 4 in-orbit validation (IOV) satellites and 14 full operational capability (FOC) satellites, 17 of which were able to transmit signal in November 2017. Galileo has already had early operational capability (EOC). To assess the latest performance of the Galileo-only precise point positioning (PPP) and the contribution of Galileo to the Multi-GNSS PPP solutions, observations collected at 16 Multi-GNSS Experiment (MGEX) stations over ten days are used to realize the various PPP cases. The statistical results show that the three-dimensional positioning accuracy of Galileo static and kinematic PPP can reach centimeter level and decimeter level after convergence, respectively. The contribution of Galileo can improve the positioning accuracy by 29.49%, 29.96% and 23.70% for GPS kinematic PPP and 11.03%, 10.59% and 11.07% for GPS/GLONASS kinematic PPP solutions in the north, east and up components, respectively. The average convergence time can be reduced by 45.48% for GPS-only kinematic PPP and by 11.04% for GPS/GLONASS solutions by adding Galileo observations. Moreover, adding Galileo observations shortens the average convergence time by 30.45% and 7.8% for GPS-only and GPS/GLONASS static PPP solutions, respectively. Although the convergent positioning results of GPS and GPS/GLONASS static PPP solutions after the addition of Galileo measurements do not demonstrate as significant improvement as those of the kinematic PPP solutions, the positioning accuracy of the GPS/Galileo static PPP solutions compared to the GPS-only static PPP still demonstrates an improvement of approximately 25% on the east component. Furthermore, the GPS/Galileo internal system time bias (ISB) and observation residual are analyzed. The results show that the noise level of the GPS L1/L2 signals and the negative impact of multipath errors on the GPS pseudo-range observations for the L1/L2 signals are greater than those of Galileo E1/E5a signals, resulting in the residuals of GPS ionosphere-free code observations larger than those of Galileo code observations. However, the phase observation residuals of GPS and Galileo are of the same magnitude. Additionally, the one-day GPS/Galileo ISB is quite stable. Its stability described by standard deviation is approximately 0.34 ns. Numéro de notice : A2019-397 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.asr.2018.06.008 date de publication en ligne : 28/06/2019 En ligne : https://doi.org/10.1016/j.asr.2018.06.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93508 [article]

Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network / Jianfeng Huang in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 151 (May 2019) . - pp 91 - 105 Titre : Automatic building extraction from high-resolution aerial images and LiDAR data using gated residual refinement network Type de document : Article/Communication Auteurs : Jianfeng Huang, Auteur ; Xinchang Zhang, Auteur ; Qinchuan Xin, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 91 - 105 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] détection du bâti [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] résidu [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] zone urbaine Résumé : (Auteur) Automated extraction of buildings from remotely sensed data is important for a wide range of applications but challenging due to difficulties in extracting semantic features from complex scenes like urban areas. The recently developed fully convolutional neural networks (FCNs) have shown to perform well on urban object extraction because of the outstanding feature learning and end-to-end pixel labeling abilities. The commonly used feature fusion or skip-connection refine modules of FCNs often overlook the problem of feature selection and could reduce the learning efficiency of the networks. In this paper, we develop an end-to-end trainable gated residual refinement network (GRRNet) that fuses high-resolution aerial images and LiDAR point clouds for building extraction. The modified residual learning network is applied as the encoder part of GRRNet to learn multi-level features from the fusion data and a gated feature labeling (GFL) unit is introduced to reduce unnecessary feature transmission and refine classification results. The proposed model - GRRNet is tested in a publicly available dataset with urban and suburban scenes. Comparison results illustrated that GRRNet has competitive building extraction performance in comparison with other approaches. The source code of the developed GRRNet is made publicly available for studies. Numéro de notice : A2019-206 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.02.019 date de publication en ligne : 20/03/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.02.019 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92669 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019053	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Calibration of the normalized radar cross section for sentinel-1 wave mode / Huimin Li in IEEE Transactions on geoscience and remote sensing, vol 57 n° 3 (March 2019)  

Permalink

Quantification of airborne lidar accuracy in coastal dunes (Fire Island, New York) / William J. Schmelz in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 2 (February 2019)  

Permalink

Improving the spatial bias correction algorithm in SMOS image reconstruction processor : validation of soil moisture retrievals with in situ data / Ali Khazaal in IEEE Transactions on geoscience and remote sensing, vol 57 n° 1 (January 2019)  

Permalink

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

Permalink

Undifferenced zenith tropospheric modeling and its application in fast ambiguity recovery for long-range network RTK reference stations / Dezhong Chen in GPS solutions, vol 23 n° 1 (January 2019)  

Permalink

Validating and comparing GNSS antenna calibrations / Ulla Kallio in Journal of geodesy, vol 93 n° 1 (January 2019)  

Permalink

A methodology for least-squares local quasi-geoid modelling using a noisy satellite-only gravity field model / R. Klees in Journal of geodesy, vol 92 n° 4 (April 2018)  

Permalink

Exploring the relationship between density and completeness of urban building data in OpenStreetMap for quality estimation / Qi Zhou in International journal of geographical information science IJGIS, vol 32 n° 1-2 (January - February 2018)  

Permalink

A posteriori bias correction of three models used for environmental reporting / Bogdan M. Strimbu in Forestry, an international journal of forest research, vol 91 n° 1 (January 2018)  

Permalink

A wavelet decomposition and polynomial fitting-based method for the estimation of time-varying residual motion error in airborne interferometric SAR / Hai Qiang Fu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Permalink