基于M-Unet的混凝土裂缝实时分割算法

针对主流深度学习裂缝分割算法消耗大量计算资源、传统图像处理方法检测精度低、丢失裂缝特征等问题，为了实现对混凝土裂缝的实时检测和在像素级水平上分割裂缝，提出一种基于轻量级卷积神经络M-Unet的裂缝语义分割模型，首先对MobileNet＿V2轻量网络进行改进，修剪其网络结构并优化激活函数，再用改进的MobileNet＿V2替换U-Net参数量巨大的编码器部分，以实现模型的轻量化并提升裂缝的分割效果。构建包含5 160张裂缝图像的SegCracks数据集对提出方法进行验证，试验结果表明：优化后的M-Unet裂缝分割效果优于U-Net、FCN8和SegNet等主流分割网络和传统图像处理技术，获得的IoU＿Score为96.10%,F1＿Score为97.99%。与改进前UNet相比，M-Unet权重文件大小减少了7%，迭代一轮时间和预测时间分别缩短了63.3%和68.6%,IoU＿Score和F1＿Score分别提升了5.79%和3.14%，并且在不同开源数据集上的交叉验证效果良好。表明提出的网络具有精度高、鲁棒性好和泛化能力强等优点。

Real-time segmentation algorithm of concrete cracks based on M-Unet

Mainstream deep learning algorithm for crack segmentation consumes a lot of computing resources while the traditional image processing methods are of low detection accuracy and lost crack features. In order to realize the real-time detection of concrete cracks and the segmentation of cracks at the pixel level, a crack semantic segmentation model based on lightweight convolutional neural network M-Unet is proposed. Firstly, the MobileNet_V2 lightweight network is improved, its network structure is trimmed and the activation function is optimized, and then the encoder part with huge parameters of U-Net is replaced by the improved MobileNet_V2 to realize the lightweight of the model and improve the segmentation effect of cracks. The SegCracks data set containing 5 160 crack images is constructed to verify the proposed method. The experimental results show that the crack segmentation effect of the optimized M-Unet is better than the mainstream segmentation networks of U-Net, FCN8 and SegNet and the traditional image processing techniques, the obtained IoU_Score is 96.10%, F1_Score is 97.99%. Compared with the original U-Net, the weight file size M-Unet is reduced by 7 %, the iteration time and prediction time are reduced by 63.3% and 68.6% respectively, and the IoU_Score and F1_Score are increased by 5.79 % and 3.14 % respectively. The cross validation results on different open source data sets are good, which shows that the proposed network has the advantages of high accuracy, good robustness and strong generalization ability.