Weather Classification for Outdoor Power Monitoring based on Improved SqueezeNet

To solve the weather classification problem in outdoor power monitoring, this paper proposes a weather classification algorithm based on improved SqueezeNet. In the proposed network, three modifications are made: Firstly, the input size is increased in the first convolution layer and the convolution kernel is reduced to make it more suitable for high-resolution image classification. Secondly, the combination of global average pooling and small fully connected layers leads to a proper tradeoff between computational burden and classification performance of the proposed network. Thirdly, the introduction of batch normalization not only suppresses the over-fitting phenomenon, but also increases classification accuracy and converging speed. According to the actual application scenario, the multi-weather image dataset is constructed and used for training and test. Experimental results verify the effectiveness of the proposed network, and reveal the proposed network, compared with the original SqueezeNet, could improve the performance of classification accuracy and suppress the over-fitting.