Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sara Akodad"'
Publikováno v:
Remote Sensing, Vol 12, Iss 20, p 3292 (2020)
Remote sensing image scene classification, which consists of labeling remote sensing images with a set of categories based on their content, has received remarkable attention for many applications such as land use mapping. Standard approaches are bas
Externí odkaz:
https://doaj.org/article/b3d5a766f29d44af8f3dc2b5b0b5f5f1
Autor:
Sara Akodad, Pierre Lassalle
The improved ability of imaging sensors to capture very high resolution (VHR) remote sensing images has been boosted by recent enhancement in the data processing algorithms. This improvement raises the potential of providing precise scene understandi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5d7fbae9a5c176b5a4e6dd4006f8103
https://doi.org/10.5194/egusphere-egu23-9983
https://doi.org/10.5194/egusphere-egu23-9983
Autor:
Sara Akodad, Lionel Bombrun, Maria Puscasu, Junshi Xia, Christian Germain, Yannick Berthoumieu
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Publikováno v:
Pattern Recognition and Artificial Intelligence ISBN: 9783031090363
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d384bf483abfbd43cc658175045d948
https://doi.org/10.1007/978-3-031-09037-0_47
https://doi.org/10.1007/978-3-031-09037-0_47
Publikováno v:
2020 IEEE International Conference on Image Processing (ICIP)
2020 IEEE International Conference on Image Processing (ICIP), Oct 2020, Abu Dhabi, United Arab Emirates. pp.3304-3308, ⟨10.1109/ICIP40778.2020.9191149⟩
ICIP
2020 IEEE International Conference on Image Processing (ICIP), Oct 2020, Abu Dhabi, United Arab Emirates. pp.3304-3308, ⟨10.1109/ICIP40778.2020.9191149⟩
ICIP
International audience; The launch of the last generation of Earth observation satellites has yield to a great improvement in the capabilities of acquiring Earth surface images, providing series of multitem-poral images. To process these time series
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4da98278672d639f0707b6b0ae79cd5
https://hal.archives-ouvertes.fr/hal-02959479
https://hal.archives-ouvertes.fr/hal-02959479
Publikováno v:
Remote Sensing
Volume 12
Issue 20
Pages: 3292
Remote Sensing, MDPI, 2020, 12 (20), pp.3292. ⟨10.3390/rs12203292⟩
Remote Sensing, Vol 12, Iss 3292, p 3292 (2020)
Volume 12
Issue 20
Pages: 3292
Remote Sensing, MDPI, 2020, 12 (20), pp.3292. ⟨10.3390/rs12203292⟩
Remote Sensing, Vol 12, Iss 3292, p 3292 (2020)
Remote sensing image scene classification, which consists of labeling remote sensing images with a set of categories based on their content, has received remarkable attention for many applications such as land use mapping. Standard approaches are bas
Autor:
Sara Akodad, Christian Germain, Yannick Berthoumieu, Lionel Bombrun, Solene Vilfroy, Charles Casimiro Cavalcante
Publikováno v:
27th European Signal Processing Conference
27th European Signal Processing Conference, Sep 2019, La Coruña, Spain
EUSIPCO
27th European Signal Processing Conference, Sep 2019, La Coruña, Spain
EUSIPCO
International audience; This paper aims at presenting a novel ensemble learning approach based on the concept of covariance pooling of CNN features issued from a pretrained model. Starting from a supervised classification algorithm, named multilayer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05d2005b247676c53bfa7145ca863b3a
https://hal.archives-ouvertes.fr/hal-02294876
https://hal.archives-ouvertes.fr/hal-02294876
Publikováno v:
IPTA
This paper introduces an image classification method based on the encoding of a set of covariance matrices. This encoding relies on Fisher vectors adapted to the log-Euclidean metric: the log-Euclidean Fisher vectors (LE FV). This approach is next ex