CNN边缘提取在冰雹预测中的应用

Study on CNN Edge Extraction in Hail Prediction

冰雹是一种破坏性较为严重的自然灾害之一.结合细胞神经网络理论对雹云进行了预测研究,选取新疆几个地区的冰雹云层图像进行分析,提供了一种简单的利用细胞神经网络边缘探测方法来判别云层图像是否降雹.在MATLAB程序进行边缘探测得到图像对应的像素矩阵数据,将矩阵数据处理得到每个图像的像素强度,像素强度小于0.8的是降雹云层,大于0.9的是无雹云层.经验证细胞神经网络理论在冰雹的预测识别中是有效的.

The hail is one of the most serious a devastating natural disaster. Bring huge losses to agriculture, architecture, communication, electric power, transportation and people＇s life and property. Chinese hail disas- ters occur frequently state, we need as soon as possible to prevent hail. This paper combines.the theory of cel- lular neural network prediction research of hail cloud. Selection of hail clouds image in several areas of Xin- jiang are analyzed, and Provides a simple use of cellular neural network edge detection method to identify whether the image of hail cloud. Edge detection of image data corresponding to the pixel matrix in the MAT- LAB program, the matrix data processing to get the pixel intensity of each image, pixel intensity is less than 0. 8 is hail clouds, greater than 0. 9 is no hail cloud. Results show that using cell neural network theory in the prediction of hail identification is effective