Learning to compare visibility on webcam images
| Autor: | Nicolas Viltard, Cécile Mallet, Pierre Lepetit, Laurent Barthès |
|---|---|
| Přispěvatelé: | SPACE - LATMOS, Laboratoire Atmosphères, Milieux, Observations Spatiales (LATMOS), Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Sorbonne Université (SU)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Sorbonne Université (SU), Sorbonne Université (SU)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS), Cardon, Catherine |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION [SDU.STU]Sciences of the Universe [physics]/Earth Sciences 02 engineering and technology Convolutional neural network [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] 020204 information systems 0202 electrical engineering electronic engineering information engineering sort Computer vision Merge sort webcam business.industry Deep learning Visibility (geometry) Process (computing) visibility [STAT.ML] Statistics [stat]/Machine Learning [stat.ML] meteorological monitoring Task (computing) ComputingMethodologies_PATTERNRECOGNITION [SDU.STU] Sciences of the Universe [physics]/Earth Sciences 020201 artificial intelligence & image processing Pairwise comparison Artificial intelligence business |
| Zdroj: | Sep 2020, 2020 Climate Informatics 2020. 10th International Conference on Climate Informatics Climate Informatics 2020. 10th International Conference on Climate Informatics, Sep 2020, Oxford, United Kingdom HAL CI |
| Popis: | International audience; From the beginning of the 2000’s, cameras are considered as an interesting source of opportunistic meteorological data. This short study deals with the comparison of meteorological visibility between images.A new dataset has been built from publicly available webcam sequences. An original labeling process, based on a mergesort algorithm, allowed us to sort more than 400 webcam sequences with respect to the meteorological visibility. Standard CNN have been trained on these sequences in a basic “learning to compare” framework and tested on independent webcams that are colocalized with visibilimeters. Results on the comparison task are promising. We observe that taking into account the numerous abstention cases improves our predictions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|