In order to solve the problem of different cost of image acquisition in different light segments,an image conversion method based on pix2pix was proposed.It mainly focuses on the generator and discriminator.In terms of generators,the residual structures generator was used instead of the original U Net generator to alleviate the gradient vanishing problem.Deformable convolution is introduced to improve the generation effect of target edges and small targets.The BAM attention mechanism is introduced to improve the feature extraction ability of the algorithm for the main target in the image to improve the image generation effect.In terms of discriminators:change the number of convolutional layers in PatchGAN (the original PatchGAN is 3 layer convolution),and set up a control experiment to find the convolutional layer with the best conversion effect.Some KAIST datasets are selected for training and testing.The experimental results show that the Root Mean Square Error (MSE) of the improved algorithm is reduced by 31.4% and the Structural Similarity (SSIM) is increased by 11.2%,which can better realize the conversion between infrared and visible images.
参考文献
相似文献
引证文献
引用本文
叶明亮,史春景,郝永平,李大伟.基于改进pix2pix的红外图像转换技术[J].激光与红外,2024,54(7):1157~1163 YE Ming-liang, SHI Chun-jing, HAO Yong-ping, LI Da-Wei. Infrared image conversion technology based on improved pix2pix[J]. LASER & INFRARED,2024,54(7):1157~1163