Foundation meteorological cloud picture classification method based on cross validation deep CNN feature integration

Abstract

The invention belongs to the technical field of ground-based meteorological cloud picture classification, and particularly relates to a ground-based meteorological cloud picture classification methodbased on cross validation deep CNN feature integration. According to the method, firstly, a convolutional neural network model is utilized to extract deep CNN features of a foundation meteorological cloud image, then multiple times of resampling of the CNN features is performed based on cross validation, and finally, identification of the cloud shape of the foundation cloud image is performed based on a voting strategy of multiple times of cross validation resampling results. According to the method, the ground-based meteorological cloud images are automatically classified, and an adaptive end-to-end automatic cloud recognition algorithm directly based on the original cloud images without any image preprocessing is realized. The proposed algorithm relates to the fields of computer vision,machine learning, image recognition and the like. The proposed algorithm fully overcomes the non-robustness of a single CNN feature cloud classification result and the high calculation overhead of multi-time deep convolutional neural network integration, and at the same time, ensures that the proposed algorithm has high classification accuracy and noise stability.

Description

technical field [0001] The invention belongs to the technical field of classification of ground-based meteorological cloud images, and in particular relates to a method for classification of ground-based meteorological cloud images based on cross-validation depth CNN feature integration. Background technique [0002] Deep convolutional neural network is one of the representative algorithms of deep learning. It is a probability model based on statistical learning. In its specific implementation algorithm, although the deep convolutional network is on the convolutional layer, pooling layer, and fully connected layer There are various variations, but from a broad perspective it always falls under the category of neural networks. In fact, the core of deep convolutional neural network is feature learning, which adaptively learns a large amount of feature information through convolution and pooling operations, and solves the defect of manually designing features in traditional mac...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of complex calculation in the cloud shape recognition process and unrobustness of the cloud shape classification result of a sing...

Images