Cloud height calculation method and system based on deep learning cloud classification algorithm
The invention provides a cloud height calculation method and system based on a deep learning cloud classification algorithm, and the method comprises the steps: obtaining a corresponding cloud classification attribute based on to-be-detected cloud image data through a pre-trained cloud classificatio...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides a cloud height calculation method and system based on a deep learning cloud classification algorithm, and the method comprises the steps: obtaining a corresponding cloud classification attribute based on to-be-detected cloud image data through a pre-trained cloud classification model; obtaining an image data set corresponding to the cloud classification attribute according to the cloud classification attribute; based on the to-be-detected cloud image data and an image data set corresponding to the cloud classification attribute, calculating association similarity between the cloud image data and image data in the image data set; determining the cloud height of the to-be-detected cloud image data according to the association similarity; according to the method, attribute classification is performed on the cloud image data by adopting the pre-trained cloud classification model, and then the cloud height of the cloud image data is determined according to the association similarity between |
---|