DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features

• Published in: IEEE transactions on geoscience and remote sensing Vol. 55; no. 10; pp. 5729 - 5740
• Main Authors: Ye, Liang, Cao, Zhiguo, Xiao, Yang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aggregation; Artificial neural networks; Classification; Cloud computing; Clouds; Computer vision; Convolutional codes; Convolutional neural network (CNN); Data mining; deep learning; Encoding; Feature extraction; Fisher vector (FV); ground-based cloud image categorization; Handicrafts; Histograms; Image classification; Mapping; Meteorology; Methods; Neural networks; Pattern analysis; pattern mining; Semantics; State of the art; Visualization

Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g...