Remote-sensing image large-magnification compression method based on lightweight deep convolutional network

Abstract

The invention discloses a remote-sensing image large-magnification compression method based on a lightweight deep convolutional network. The method comprises the following steps: 1, constructing the lightweight deep convolutional network with seven layers; 2, selecting a remote-sensing image training sample; 3, generating a training data set; 4, training the lightweight deep convolutional network;5, compressing the to-be-tested remote-sensing image; and 6, decompressing a large-magnification compressed file of the to-be-tested remote-sensing image. A new lightweight deep convolutional networkwith seven layers is designed through the method disclosed by the invention; the model of the method is light and handy, the compression and decompression time are short, the large magnification compression is realized, the inverse quantization is optimized, the precision of the neural network is improved, the restored remote-sensing image quality is improved, and the edge texture information ofmore remote-sensing image can be reserved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a large-magnification compression method for remote sensing images based on a lightweight deep convolutional network in the technical field of image compression. The invention can be used for real-time high-magnification compression of remote sensing images captured by satellites in orbit. Background technique [0002] At present, with the rapid increase in the number of satellites in orbit in my country, the amount of collected remote sensing image data is increasing exponentially, and the contradiction between information acquisition and data transmission will become increasingly serious. become increasingly urgent. [0003] Xidian University disclosed a large compression method of deep self-encoding network in its patent document "Satellite remote sensing image compression method with large compression ratio based on deep self-encoding network" (patent applicati...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are that since this method needs to cascade and stack multiple autoencoders to form a deep autoencoder network, it needs to be trained multiple times, the training is complex, the number of parameters is large, the training time is long, and the algorithm complexity High, and this method will lose the accuracy of the network in the process of quantization and dequantization, and reduce the reconstruction quality of remote sensing images

Although this method has achieved a certain compression effect, the disadvantage of this method is that when the magnification increases, the wavelet transform will lose a large number of high-frequency coefficients, resulting in a large loss of texture and edge features of the original remote sensing image.

Images