Remote sensing . vol 14 n° 18Paru le : 15/09/2022 |
[n° ou bulletin]
[n° ou bulletin]
|
Dépouillements
Ajouter le résultat dans votre panierComparison of deep neural networks in detecting field grapevine diseases using transfer learning / Antonios Morellos in Remote sensing, vol 14 n° 18 (September-2 2022)
[article]
Titre : Comparison of deep neural networks in detecting field grapevine diseases using transfer learning Type de document : Article/Communication Auteurs : Antonios Morellos, Auteur ; Xanthoula Eirini Pantazi, Auteur ; Charalampos Paraskevas, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4648 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de changement
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] Grèce
[Termes IGN] jeu de données
[Termes IGN] maladie cryptogamique
[Termes IGN] maladie phytosanitaire
[Termes IGN] viticultureRésumé : (auteur) Plants diseases constitute a substantial threat for farmers given the high economic and environmental impact of their treatment. Detecting possible pathogen threats in plants based on non-destructive remote sensing and computer vision methods offers an alternative to existing laboratory methods and leads to improved crop management. Vine is an important crop that is mainly affected by fungal diseases. In this study, photos from healthy leaves and leaves infected by a fungal disease of vine are used to create disease identification classifiers. The transfer learning technique was employed in this study and was used to train three different deep convolutional neural network (DCNN) approaches that were compared according to their classification accuracy, namely AlexNet, VGG-19, and Inception v3. The above-mentioned models were trained on the open-source PlantVillage dataset using two training approaches: feature extraction, where the weights of the base deep neural network model were frozen and only the ones on the newly added layers were updated, and fine tuning, where the weights of the base model were also updated during training. Then, the created models were validated on the PlantVillage dataset and retrained using a custom field-grown vine photo dataset. The results showed that the fine-tuning approach showed better validation and testing accuracy, for all DCNNs, compared to the feature extraction approach. As far as the results of DCNNs are concerned, the Inception v3 algorithm outperformed VGG-19 and AlexNet in almost all the cases, demonstrating a validation performance of 100% for the fine-tuned strategy on the PlantVillage dataset and an accuracy of 83.3% for the respective strategy on a custom vine disease use case dataset, while AlexNet achieved 87.5% validation and 66.7% accuracy for the respective scenarios. Regarding VGG-19, the validation performance reached 100%, with an accuracy of 76.7%. Numéro de notice : A2022-768 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14184648 Date de publication en ligne : 17/09/2022 En ligne : https://doi.org/10.3390/rs14184648 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101794
in Remote sensing > vol 14 n° 18 (September-2 2022) . - n° 4648[article]3D LiDAR aided GNSS/INS integration fault detection, localization and integrity assessment in urban canyons / Zhipeng Wang in Remote sensing, vol 14 n° 18 (September-2 2022)
[article]
Titre : 3D LiDAR aided GNSS/INS integration fault detection, localization and integrity assessment in urban canyons Type de document : Article/Communication Auteurs : Zhipeng Wang, Auteur ; Bo Li, Auteur ; Zhiqiang Dan, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4641 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] canyon urbain
[Termes IGN] couplage GNSS-INS
[Termes IGN] détection de cible
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] erreur de positionnement
[Termes IGN] filtre adaptatif
[Termes IGN] intégration de données
[Termes IGN] intégrité des données
[Termes IGN] khi carré
[Termes IGN] semis de pointsRésumé : (auteur) The performance of Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS) integrated navigation can be severely degraded in urban canyons due to the non-line-of-sight (NLOS) signals and multipath effects. Therefore, to achieve a high-precision and robust integrated system, real-time fault detection and localization algorithms are needed to ensure integrity. Currently, the residual chi-square test is used for fault detection in the positioning domain, but it has poor sensitivity when faults disappear. Three-dimensional (3D) light detection and ranging (LiDAR) has good positioning performance in complex environments. First, a LiDAR aided real-time fault detection algorithm is proposed. A test statistic is constructed by the mean deviation of the matched targets, and a dynamic threshold is constructed by a sliding window. Second, to solve the problem that measurement noise is estimated by prior modeling with a certain error, a LiDAR aided real-time measurement noise estimation based on adaptive filter localization algorithm is proposed according to the position deviations of matched targets. Finally, the integrity of the integrated system is assessed. The error bound of integrated positioning is innovatively verified with real test data. We conduct two experiments with a vehicle going through a viaduct and a floor hole, which, represent mid and deep urban canyons, respectively. The experimental results show that in terms of fault detection, the fault could be detected in mid urban canyons and the response time of fault disappearance is reduced by 70.24% in deep urban canyons. Thus, the poor sensitivity of the residual chi-square test for fault disappearance is improved. In terms of localization, the proposed algorithm is compared with the optimal fading factor adaptive filter (OFFAF) and the extended Kalman filter (EKF). The proposed algorithm is the most effective, and the Root Mean Square Error (RMSE) in the east and north is reduced by 12.98% and 35.1% in deep urban canyons. Regarding integrity assessment, the error bound can overbound the positioning errors in deep urban canyons relative to the EKF and the mean value of the error bounds is reduced. Numéro de notice : A2022-769 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article DOI : 10.3390/rs14184641 Date de publication en ligne : 16/09/2022 En ligne : https://doi.org/10.3390/rs14184641 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101795
in Remote sensing > vol 14 n° 18 (September-2 2022) . - n° 4641[article]Estimation of swell height using spaceborne GNSS-R data from eight CYGNSS satellites / Yanli Zheng in Remote sensing, vol 14 n° 18 (September-2 2022)
[article]
Titre : Estimation of swell height using spaceborne GNSS-R data from eight CYGNSS satellites Type de document : Article/Communication Auteurs : Yanli Zheng, Auteur ; Fu Zheng, Auteur ; Cheng Yang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4640 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] données GLONASS
[Termes IGN] données GPS
[Termes IGN] double différence
[Termes IGN] latitude
[Termes IGN] positionnement ponctuel précis
[Termes IGN] positionnement statique
[Termes IGN] retard troposphérique zénithal
[Termes IGN] temps de convergenceRésumé : (auteur) The orbital inclination angle of the GLONASS constellation is about 10° larger than that of GPS, Galileo, and BDS. Theoretically, the higher orbital inclination angle could provide better observation geometry in high latitude regions. A wealth of research has investigated the positioning accuracy of GLONASS and its impact on multi-GNSS, but rarely considered the contribution of the GLONASS constellation’s large orbit inclination angle. The performance of GLONASS in different latitude regions is evaluated in both stand-alone mode and integration with GPS in this paper. The performance of GPS is also presented for comparison. Three international GNSS service (IGS) networks located in high, middle, and low latitudes are selected for the current study. Multi-GNSS data between January 2021 and June 2021 are used for the assessment. The data quality check shows that the GLONASS data integrity is significantly lower than that of GPS. The constellation visibility analysis indicates that GLONASS has a much better elevation distribution than GPS in high latitude regions. Both daily double-difference network solutions and daily static Precise Point Positioning (PPP) solutions are evaluated. The statistical analysis of coordinate estimates indicates that, in high latitude regions, GLONASS has a comparable or even better accuracy than that of GPS, and GPS+GLONASS presents the best estimate accuracy; in middle latitude regions, GPS stand-alone constellation provides the best positioning accuracy; in low latitude regions, GLONASS offers the worst accuracy, but the positioning accuracy of GPS+GLONASS is better than that of GPS. The tropospheric estimates of GLONASS do not present a resemblance regional advantage as coordinate estimates, which is worse than that of GPS in all three networks. The PPP processing with combined GPS and GLONASS observations reduces the convergence time and improves the accuracy of tropospheric estimates in all three networks. Numéro de notice : A2022-770 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.3390/rs14184640 Date de publication en ligne : 16/09/2022 En ligne : https://doi.org/10.3390/rs14184640 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101796
in Remote sensing > vol 14 n° 18 (September-2 2022) . - n° 4640[article]