Sorting method of ground-based visible light cloud picture

Abstract

The invention discloses a sorting method of a ground-based visible light cloud picture. The method comprises the following steps that 1, image preprocessing is performed on the ground-based visible light cloud picture to obtain standard cloud pictures, a plurality of images are selected randomly from the standard cloud pictures to be used as training samples, the rest are used as testing samples, and the number of the training samples is larger than that of the testing samples; 2, global features of the standard cloud pictures are extracted, and comprise textural features and color features, and the texture features comprise gray level co-occurrence matrixes and Tamura features; 3, a bag of words model is built on basis of SIFT (Scale-Invariant Feature Transform) feature descriptors, and local features of the standard cloud pictures are extracted; 4, the global features obtained in the step 2 and the local features obtained in the step 3 are linearly fused, and a limitation learning machine model is built for the training samples to obtain a cloud picture classifier; 5, sorting is performed on the testing samples by using the cloud picture classifier, and a final sorting result is obtained. The sorting is more accurate by using the sorting method of the ground-based visible light cloud picture.

Description

technical field [0001] The invention relates to a classification method for ground-based visible light cloud images, belonging to the technical fields of image information processing and meteorology. Background technique [0002] Clouds are an important part of the earth's heat balance and water-air cycle. The changes of clouds determine the earth's radiation budget and are an important factor in global climate change. Therefore, determining the type of cloud and understanding the distribution of cloud are crucial to the accuracy of weather forecast, the effectiveness of climate monitoring, the scientific nature of climate model establishment, and atmospheric sounding and atmospheric remote sensing. [0003] Satellite cloud images can provide information on the large-scale distribution and structure of large-scale clouds, but are limited by spatial resolution and unknown surface effects on thin and low clouds; while ground-based cloud observations have a small range and can ...

AI Technical Summary

Problems solved by technology

The K-nearest neighbor method is easily affected by the selection of the initial center of the category; the classic support vector machine only provides a binary classification algorithm, which is difficult to implement for large-scale training samples; the Bayesian classifier needs to know the exact distribution probability of each category, and in In practice, these factors are often unpredictable; the traditional neural network adopts the gradient learning method (BP) of error feedback, which has the disadvantages of slow learning speed, too many iterations, and the solution is easy to fall into local minimum.

Images