TCS-Net:一种核电安全壳细小裂缝分割网络

TCS-Net:A Tiny Crack Segmentation Network for Nuclear Containment Vessel

针对核电安全壳表面裂缝视觉检查任务面临的裂缝细小且占像素少、裂缝与背景对比度低、相似纹理干扰多、光照不均衡等问题,作者提出了一种细小裂缝分割模型(segmentation network of tiny cracks,TCS-Net)。该模型具有与U-Net网络相似的编码-解码结构,在下采样过程使用软池化(soft pooling)可实现在编码过程中保存原始图像基本特征的同时又保持了高响应特征信息的放大,从而减少信息损失实现裂缝边缘细节及位置信息保留;解码端在上采样过程中加入兼顾通道注意力和空间注意力的语义补偿模块以融合编码端的各层特征,可增强裂缝的多尺度细节信息;鉴于裂缝分割任务存在数据不平衡的分类问题,为避免训练过程被多数类(背景像素)所主导,TCS-Net模型结合二元交叉熵损失和Dice系数作为目标损失函数,以解决单一损失关注度倾向带来的训练不稳定的问题,也可优化准确率、交并比、召回率等性能指标。该模型在真实的安全壳图像上实验,结果表明,与现有的主流语义分割模型相比,TCS-Net裂缝分割模型的交并比指标可提高5%~9%,召回率指标可提高9%~13%,由此说明该模型具有检测率和检测精度更高,能有效适用于目标与背景严重不平衡、背景复杂且干扰较多情况下的细小裂缝分割任务。

A segmentation network of Tiny cracks(TCS-Net)is proposed to solve the problems of small cracks with few pixels,low contrast between cracks and background,much interferences from similar textures,and uneven illumination.TCS-Net has a coding-decoding structure similar to that of U-Net network.The soft Pooling was used in down-sampling process to preserve the basic features of original images while maintaining the amplification of high-response features,thus reducing information loss and preserving the details and location of crack edges.In the up-sampling process,a semantic compensation module combining channel attention and spatial attention was added at the decoding end to fuse the features of each layer at the coding end,which could enhance the multi-scale details of cracks.In view of the classification problem of unbalanced data in crack segmentation task,in order to avoid the training process being dominated by most classes(background pixels),the binary cross entropy loss and Dice coefficient were combined by TCS-Net model as the objective loss function to solve the problem of training instability caused by attention tendency of single loss.It can also optimize performance indicators such as accuracy,crossover ratio and recall rate.The proposed fracture segmentation model was tested on a real containment image.Experimental results show that,compared with the existing mainstream semantic segmentation models,TCS-Net fracture segmentation model improves the intersection over union ratio index by 5%~9%and recall ratio index by 9%~13%,which demonstrates that the model achieves higher detection rate and detection accuracy.The proposed TCS-Net canbe effectively applied to the fine crack segmentation task under the conditions of serious imbalance between target and background,complex background with many disturbances.