激光与光电子学进展, 2019, 56 (16): 160101, 网络出版: 2019-08-05
基于多尺度卷积特征融合的台风等级分类模型 下载: 904次
Typhoon Classification Model Based on Multi-Scale Convolution Feature Fusion
大气光学 台风等级分类 卷积神经网络 多尺度特征 尺度不变损失函数 atmospheric optics typhoon classification convolutional neural network multi-scale feature loss function with scale invariance
摘要
为提高卷积神经网络对图像多尺度变化的感知能力,增加网络的尺度不变性,提出一种基于多尺度卷积特征融合的台风等级分类模型。在卷积神经网络中添加多尺度感知层,对卷积特征进行多尺度感知并进行级联。将多尺度正则化项添加到损失函数中,通过反向传播来最小化隐含层权重的残差,优化模型的特征提取能力。最后将多尺度高层语义特征通过Softmax分类层归一化成各图像类别的概率值,取最大概率值为最后图像的分类结果。为有效验证本模型的多尺度感知能力,选用红外卫星台风云图作为数据集,实验结果表明,本模型能有效感知并提取台风云图的局部特征,并在两个通用数据集MNIST和CIFAR-10上验证了本模型的泛化能力。
Abstract
In order to enhance the perception for the multi-scale image variation and improve the scale invariance of convolutional neural networks,this study proposes a typhoon classification model based on multi-scale convolutional feature fusion. A multi-scale perception layer is added to convolutional neural networks; then, convolutional features are multi-scale perceived and cascaded. A multi-scale regularization term is then incorporated into the loss function. The residual error of hidden layer weight is minimized and the feature extraction ability is optimized with backpropagation. Finally, multi-scale high-level semantic features are normalized to the probability value of each category using Softmax. The maximum probability value is used as the final classification result of the image. Infrared satellite cloud images are used as the dataset in our experiments to validate the multi-scale perception ability of the model. Experimental results show that the model can effectively perceive and extract the local features of the typhoon cloud map. The generalization ability of the model is verified using two general datasets, i.e., MNIST and CIFAR-10.
卢鹏, 邹佩岐, 邹国良. 基于多尺度卷积特征融合的台风等级分类模型[J]. 激光与光电子学进展, 2019, 56(16): 160101. Peng Lu, Peiqi Zou, Guoliang Zou. Typhoon Classification Model Based on Multi-Scale Convolution Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(16): 160101.