Multispectral image compression method and system based on multidirectional convolutional neural network

The invention discloses a multispectral image compression method and system based on a multidirectional convolutional neural network. The system comprises a forward coding network, a quantization module, an entropy coding module, an entropy decoding module, an inverse quantization module and a reverse decoding network. The method specifically comprises the following steps: constructing a multispectral image compression network and training the multispectral image compression network to obtain an optimal multispectral image compression network model; sending a to-be-compressed multispectral image into a multispectral image compression network, extracting inter-spectral spatial features of the image through multidirectional convolution, reducing the size of a feature map through downsampling after dimension reduction fusion, removing data redundancy through quantization, and obtaining a compressed code stream used for transmission and storage through lossless entropy coding; and performing entropy decoding and