A large compression ratio satellite remote sensing image compression method based on deep autoencoder network

Abstract

The invention discloses a large-compression-ratio satellite remote sensing image compression method based on a deep self-encoding network, and mainly aims to solve the problem of low compression ratio in the prior art. The method comprises the following implementation steps: cascading and stacking a plurality of self-encoders to construct the deep self-encoding network; inputting a group of training image data to the deep self-encoding network, and training the network to obtain optimized network parameters in order to obtain a deep compression network and a deep decompression network; transmitting a remote sensing image to be compressed into the deep compression network to obtain high-order sparse features, and quantifying and encoding the features to obtain final compressed code streams; and inversely quantifying and encoding the received code streams to obtain the high-order sparse features, and transmitting the high-order sparse features to the deep decompression network, wherein a final output of the network is a decompressed remote sensing image. Image processing and deep learning technologies are combined, so that large-ratio compression of satellite remote sensing data is realized. Only simple forward transmission operation is required in compressing and decompressing processes, so that high timeliness is achieved, and the storage and transmission burdens of massive remote sensing data are relieved.

Description

Technical field: [0001] The invention belongs to the technical field of image processing and machine learning, and further relates to a compression method for remote sensing images, specifically a method for compressing satellite remote sensing images with a large compression ratio based on a deep self-encoding network, which can be used for on-orbit real-time large magnification of satellite remote sensing images Compression, storage and transmission, natural scene images. Background technique: [0002] Remote sensing is an important application of spatial information network, and plays an important role in many fields such as environment, transportation, ocean, agriculture, water conservancy, surveying and mapping, and geology. With the development of new satellite data services and new sensors, the amount of satellite remote sensing data in my country is growing exponentially. Massive high-resolution satellite remote sensing data not only brings higher quality data source...

AI Technical Summary

Problems solved by technology

[0006] At present, there are few feature-level compression methods for remote sensing images, mainly linear sparse coding methods based on dictionary learning. Linear sparse coding is a data representation model under a "shallow architecture" that can only learn low-level features such as edge directions. The low-level features of , although the sparse description space can be obtained through dictionary learning, often cannot mine the hidden explanatory factors of complex unstructured scenes

Images