Heterospectral Infrared Image Transformation Method Based on Gradient Constrained Generative Adversarial Network

Abstract

The invention discloses a method for transforming infrared images of heterospectral bands based on a gradient-constrained generation confrontation network, which includes: using a generation sub-network to transform an infrared image to be tested into an infrared image of a hetero-spectrum band, and the training of the generation sub-network includes: The paired infrared images of two spectral bands are paired into training sample pairs and test sample pairs, and the generation confrontation network is constructed. Constrained loss function, calculate the loss of the discriminator sub-network and the generation sub-network, back propagation update the discriminant sub-network and the generation sub-network; divide the test sample pair into several test image blocks, use the test image blocks to test the generation sub-network, get Transform the picture, when the mean value of the local correlation value between the transformed picture and the test image block is greater than or equal to the threshold, a trained generation sub-network is obtained. The results of the image transformation of the present invention are better.

Description

Technical field [0001] The invention belongs to the field of infrared image processing, and more specifically, relates to a method for transforming infrared images of different spectrum bands based on gradient constraint generation counter-network. Background technique [0002] With the advancement of science and technology and the continuous development of camouflage and jamming technologies, single-band broadband target detection and recognition can no longer meet the needs of target recognition under complex conditions. Multi-band detection and multi-feature information fusion technology will soon become an important means of target recognition. Infrared multi-spectral images can provide not only the spatial information of the target, but also the spectral information of the target, which provides an analytical data basis for the feature extraction, fusion and recognition of infrared targets. [0003] The rapid development of infrared imaging technology and its significant appli...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a heterospectral infrared image transformation method based on a gradient-constrained generative adversarial network, thereby solving the problem of high cost, time-consuming, and difficulty in obtaining an approximate real scene in the prior art. Technical Issues of Multispectral Simulation Images

Images