基于Pix2Pix模型的康普顿相机图像重建优化研究  

Optimization study of Compton camera image reconstruction based on Pix2Pix model

作　　者：赵丽文 卢棚 金龙泉 宋耀洲 ZHAO Li-wen;LU Peng;JIN Long-quan;SONG Yao-zhou(School of Computer Science and Engineering,Anhui University of Science and Technology,Anhui Huainan 232001,China;Institute of Energy,Hefei Comprehensive National Science Center(Anhui Energy Laboratory),Anhui Hefei 230031,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001 [2]合肥综合性国家科学中心能源研究院(安徽省能源实验室),安徽合肥230031

出　　处：《齐齐哈尔大学学报(自然科学版)》2025年第1期43-49,共7页Journal of Qiqihar University(Natural Science Edition)

基　　金：国家自然科学基金(12105135);安徽高校协同创新项目(GXXT-2022-004);合肥综合性国家科学中心能源研究院(安徽省能源实验室)项目(21KZS202,21KZS208)。

摘　　要：为改善康普顿相机传统重建算法中重建质量差、重建速度慢的问题,使用基于Pix2Pix深度学习模型的康普顿相机重建算法优化重建图像质量。首先,通过蒙特卡罗方法模拟康普顿相机获取实验数据过程,制作部分数据集,并利用数据增强技术扩充模型所需数据集。其次,通过在生成器引入16层的U-Net模型,并结合SimAM模块,增强模型的特征提取能力,降低模型训练中模式崩塌的可能性。最后,在判别器中加入残差模块,使模型训练过程更稳定,提升模型性能。实验结果表明,在提升传统重建方法图像质量的基础上,峰值信噪比较原模型提升了3.05,结构相似性提升了1.83%。To improve the problems of poor reconstruction quality and slow reconstruction speed in the traditional reconstruction algorithm of Compton camera,the reconstruction algorithm of Compton camera based on Pix2Pix deep learning model is used to optimize the reconstructed image quality.Firstly,the process of acquiring experimental data from Compton camera is simulated by Monte Carlo method to produce a partial dataset,and the dataset required for the model is expanded using data enhancement techniques.Secondly,by introducing a 16-layer U-Net model in the generator and combining it with the SimAM module,it enhances the feature extraction capability of the model and reduces the possibility of pattern collapse during model training.Finally,the residual module is added to the discriminator,which makes the model training process more stable and improves the model performance.The experimental results show that on the basis of improving the image quality of the traditional reconstruction method,PSNR is improved by 3.05 and the SSIM is improved by 1.83%compared with the original model.

关 键 词：SimAM 康普顿相机 Pix2Pix 重建算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]