局部聚类分析的FCN-CNN云图分割方法

空气中的尘埃、污染物及气溶胶粒子的存在严重影响了大气预测的有效性,毫米波雷达云图的有效分割成为了解决这一问题的关键.本文提出了一种基于超像素分析的全卷积神经网路FCN和深度卷积神经网络CNN（FCN-CNN）的云图分割方法.首先通过超像素分析对云图每个像素点的近邻域实现相应的聚类,同时将云图输入到不同步长的全卷积神经网络FCN32s和FCN8s中实现云图的预分割;FCN32s预测结果中的"非云"区域一定是云图中的部分"非云"区域,FCN8s预测结果中的"云"区域一定是云图中的部分"云"区域;剩下不确定的区域通过深度卷积神经网络CNN进行进一步分析.为提高效率,FCN-CNN选取了不确定区域中超像素的几个关键像素来代表超像素区域的特征,通过CNN网络来判断关键像素是"云"或者是"非云".实验结果表明,FCN-CNN的精度与MR-CNN、SP-CNN相当,但是速度相比于MR-CNN提高了880倍,相比于SP-CNN提高了1.657倍.

Local Clustering Analysis Based FCN-CNN for Cloud Image Segmentation

Dust, pollutant and the aerosol particles in the air brings significant challenge to the atmospheric prediction, and the segmentation of millimeter-wave radar cloud image has become a key to deal with the problem. This paper presents superpixel analysis based cloud image segmentation with fully convolutional networks (FCN) and convolutional neural networks (CNN), named FCN-CNN. Firstly, the superpixel analysis is performed to cluster the neighborhood of each pixel in the cloud image. Then the cloud image is given to the FCN with different steps, such as FCN32s and FCN8s. The "non-cloud" area in the FCN32s result must be a part of the "non-cloud" area in the cloud image. Meanwhile, the "cloud" area in the FCN8s result must be a part of the "cloud" area in the cloud image. The remaining uncertain region of the cloud image needs to be further estimated by CNN. For efficiency, it is necessary to select several key pixels in the superpixel to represent the characteristics of the superpixel region. The selected key pixels are classified by CNN as "cloud" or "non-cloud". The experimental results illustrate that the accuracy of FCN-CNN is almost equivalent to MR-CNN and SP-CNN, but the speed is 880 times higher than MR-CNN, and 1.657 times higher than SP-CNN.