改进多阶段渐进式的受电弓碳滑板图像去模糊  

Rail pantograph carbon strip image deblurring based on improved multi-stage progressive image restoration

作　　者：刘伟民 张梦准 郑爱云 刘晋 郑直 Liu Weimin;Zhang Mengzhun;Zheng Aiyun;Liu Jin;Zheng Zhi(College of Mechanical Engineering,North China University of Science and Technology,Tangshan 063210,China;CRRC Tangshan Co.,Ltd.,Tangshan 064000,China)

机构地区：[1]华北理工大学机械工程学院,唐山063210 [2]中车唐山机车车辆有限公司,唐山064000

出　　处：《电子测量技术》2024年第5期85-93,共9页Electronic Measurement Technology

基　　金：河北省科技重大专项(22282203Z);河北省自然科学基金(E2022209086)项目资助。

摘　　要：针对高铁运行速度过快,容易导致受电弓碳滑板的监测图像出现运动模糊问题,提出了一种改进多阶段渐进式网络的图像去模糊方法。首先,引入混合膨胀卷积作为特征提取网络,在不改变计算量和特征图分辨率前提下,可以增大局部感受野,进而可获取高质量的图像纹理和细节信息;其次,引入像素点注意力机制,自适应地选择每个像素点的权重值,增强模型去模糊质量;再次,引入混合损失函数,提高模型对不同类型模糊的鲁棒性;最后,制作1600对受电弓碳滑板监测图像合成数据集以供模型进行训练和测试。为了评估所提网络的去模糊效果,将训练所得模型在上述数据集上进行了测试,实验结果表明峰值信噪比达到了38.82 dB、结构相似性达到了0.9723,在视觉上较另外7种经典方法能更好地复原图像的边缘轮廓和纹理细节信息。有效地提升了模型的鲁棒性。Objective:To solve the problem of motion blur in the monitoring image of the pantograph carbon slide caused by the fast running speed of high-speed railway,an image deblurring method based on improved multi-stage progressive network is proposed.Methods:First,a hybrid dilated convolution is introduced as a feature extraction network,which can increase the local receptive field without changing the calculation and resolution of the feature map,and then obtain high-quality image texture and detail information.Secondly,the pixel attention mechanism was introduced to adaptively select the weight value of each pixel to enhance the deblurring quality of the model.Thirdly,a hybrid loss function was introduced to improve the robustness of the model to different types of fuzziness.Finally,a synthetic data set of 1600 pairs of pantograph carbon slide monitoring images was made for the model to train and test.The experimental results show that the peak signal-to-noise ratio(PSNR)reaches 38.82 dB and the structural similarity(SSIM)reaches 0.9723.Compared with the other seven classical methods,the proposed network can better restore the edge contour and texture detail information of the image.The robustness of the model is effectively improved.

关 键 词：图像去模糊 卷积神经网络 混合膨胀卷积 像素点注意力 混合损失函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]