Centre de documentation
scientifique

Dépouillements

Unsupervised self-adaptive deep learning classification network based on the optic nerve microsaccade mechanism for unmanned aerial vehicle remote sensing image classification / Ming Cong in Geocarto international, vol 36 n° 18 ([01/10/2021])  

Public [article]  inGeocarto international > vol 36 n° 18 [01/10/2021] . - pp 2065 - 2084 Titre : Unsupervised self-adaptive deep learning classification network based on the optic nerve microsaccade mechanism for unmanned aerial vehicle remote sensing image classification Type de document : Article/Communication Auteurs : Ming Cong, Auteur ; Zhiye Wang, Auteur ; Yiting Tao, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2065 - 2084 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] chromatopsie [Termes IGN] classification non dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] compréhension de l'image [Termes IGN] échantillonnage d'image [Termes IGN] filtrage numérique d'image [Termes IGN] image captée par drone [Termes IGN] vision [Termes IGN] vision par ordinateur Résumé : (auteur) Unmanned aerial vehicle remote sensing images need to be precisely and efficiently classified. However, complex ground scenes produced by ultra-high ground resolution, data uniqueness caused by multi-perspective observations, and need for manual labelling make it difficult for current popular deep learning networks to obtain reliable references from heterogeneous samples. To address these problems, this paper proposes an optic nerve microsaccade (ONMS) classification network, developed based on multiple dilated convolution. ONMS first applies a Laplacian of Gaussian filter to find typical features of ground objects and establishes class labels using adaptive clustering. Then, using an image pyramid, multi-scale image data are mapped to the class labels adaptively to generate homologous reliable samples. Finally, an end-to-end multi-scale neural network is applied for classification. Experimental results show that ONMS significantly reduces sample labelling costs while retaining high cognitive performance, classification accuracy, and noise resistance—indicating that it has significant application advantages. Numéro de notice : A2021-707 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/10106049.2019.1687593 Date de publication en ligne : 07/11/2019 En ligne : https://doi.org/10.1080/10106049.2019.1687593 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98602 [article]

Field scale wheat LAI retrieval from multispectral Sentinel 2A-MSI and LandSat 8-OLI imagery: effect of atmospheric correction, image resolutions and inversion techniques / Rajkumar Dhakar in Geocarto international, vol 36 n° 18 ([01/10/2021])  

Public [article]  inGeocarto international > vol 36 n° 18 [01/10/2021] . - pp 2044 - 2064 Titre : Field scale wheat LAI retrieval from multispectral Sentinel 2A-MSI and LandSat 8-OLI imagery: effect of atmospheric correction, image resolutions and inversion techniques Type de document : Article/Communication Auteurs : Rajkumar Dhakar, Auteur ; Vinay Kumar Sehgal, Auteur ; Debasish Chakraborty, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2044 - 2064 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] blé (céréale) [Termes IGN] correction atmosphérique [Termes IGN] image Landsat-OLI [Termes IGN] image multibande [Termes IGN] image proche infrarouge [Termes IGN] image Sentinel-MSI [Termes IGN] Inde [Termes IGN] indice foliaire [Termes IGN] Leaf Area Index [Termes IGN] pouvoir de résolution géométrique [Termes IGN] réseau neuronal artificiel Résumé : (auteur) This study assessed the effect of atmospheric correction algorithms, inversion techniques and image spatial and spectral resolution on wheat crop LAI retrieval using Sentinel-2 MSI and Landsat-8 OLI imagery. The LAI retrievals were validated with in-situ measurements collected in farmers’ fields. The MSI-based LAI retrievals improved significantly when images were atmospherically corrected using MODTRAN than using the libRadtran code. Among the two PROSAIL inversion approaches, look-up table outperforms artificial neural network for LAI retrievals. Using the best strategy of atmospheric correction and inversion, the effect of spatial resolution from 20 m (MSI) to 30 m (OLI) while using common six bands, showed non-significant improvement in LAI retrievals. The inclusion of additional two red-edge bands as available in MSI significantly reduced the uncertainly in LAI retrievals over that obtained by using six bands, while inclusion of only additional VNIR band did not show any significant effect on LAI retrievals. Numéro de notice : A2021-742 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1687591 Date de publication en ligne : 12/11/2019 En ligne : https://doi.org/10.1080/10106049.2019.1687591 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98666 [article]

Spatial biodiversity modeling using high-performance computing cluster: A case study to access biological richness in Indian landscape / Hariom Singh in Geocarto international, vol 36 n° 18 ([01/10/2021])  

Public [article]  inGeocarto international > vol 36 n° 18 [01/10/2021] . - pp 2023 - 2043 Titre : Spatial biodiversity modeling using high-performance computing cluster: A case study to access biological richness in Indian landscape Type de document : Article/Communication Auteurs : Hariom Singh, Auteur ; R.D. Garg, Auteur ; Harish Chandra Karnatak, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2023 - 2043 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] autocorrélation spatiale [Termes IGN] biodiversité [Termes IGN] coefficient de corrélation [Termes IGN] distribution spatiale [Termes IGN] Inde [Termes IGN] processus de hiérarchisation analytique [Termes IGN] regroupement de données [Termes IGN] relevé phytosociologique [Termes IGN] SIG participatif Résumé : (auteur) The parallel processing and distributed GIServices provide an efficient approach to address the geocomputation challenges in biodiversity modeling. Using the widely applied Spatial Biodiversity Model (SBM) as an illustration, this study demonstrates parallelization of the spatial landscape algorithms based on Message Passing Interface (MPI) in cluster computing. The geocomputation based on MPI is performed to characterize the spatial distribution of Biological Richness (BR) for Indian landscape using developed high-performance cluster computing-based model named as SBM-HPC. In performance analysis, the execution time is reduced by 56.42%–81.41% (or the speedups of 2.29–5.38) using the parallel and cluster computing environment. Also, the spatial landscape algorithms of the model are extended to integrate large-scale geodata from online map services archives using distributed GIServices. To validate BR map, the phytosociological data is collected using participatory GIS approach. Furthermore, regression analysis between derived BR map and Shannon-Wiener index (Hˈ) represents high correlation coefficient R2 values. Highlights : - Development of spatial biodiversity model using parallel computing on the cluster. - Geocomputation of spatial landscape indices using large-scale geospatial datasets. - Distributed GIService integration in model to compute distributed data archives. - Prediction of biological richness pattern and validation using participatory GIS. - Characterize correlations between biological richness and bioclimatic patterns. Numéro de notice : A2021-763 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1678679 Date de publication en ligne : 21/10/2019 En ligne : https://doi.org/10.1080/10106049.2019.1678679 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98798 [article]