Abstract: Aiming at the weak effect of basic U-Net on pavement crack segmentation, insufficient fineness of crack contour segmentation, difficulty in identifying narrow cracks, and low segmentation accuracy, this paper proposes an improved U-Net-based pavement crack segmentation method. Firstly, the improved ResNet50 is used as the backbone network to extract the pavement crack features, secondly, an attention mechanism-based feature fusion module is designed to improve the jump connection of U-Net, and finally, the improved model is obtained by adding the feature refinement head in the decoding part. The self-built pavement crack dataset is used to compare the proposed model with the current state-of-the-art models, and ablation experiments are done for the model before and after optimization. The experimental results show that the mIoU, Precision, and mPA of the proposed model on the self-built pavement crack dataset reach 0.838 1, 0.892 8, and 0.916 9, respectively, which are 0.019, 0.016 8, and 0.023 2 higher than the baseline U-Net, and the inference speed of 40.02 FPS can meet the needs of engineering applications. Finally, it is verified in the open-source Crack500 dataset that the model in this paper has stronger performance and generalization ability compared with network models such as U-Net and DeepLabV3+.

Key words: computer applications, pavement crack detection, deep learning, feature fusion, semantic segmentation

摘要： 针对基础U-Net对路面裂缝分割效果不强，裂缝轮廓分割精细度不够、难以识别狭窄裂缝、分割精度低等问题，提出一种改进U-Net的路面裂缝分割方法。使用改进的ResNet50作为主干网络提取路面裂缝特征，设计了基于注意力机制的特征融合模块改进U-Net的跳跃连接，在解码部分添加特征细化头得到改进的模型。使用自建的路面裂缝数据集对提出的模型与目前先进模型进行比较，并对优化前后的模型做消融实验。实验结果表明，该模型在自建的路面裂缝数据集上的mIoU、Precision、mPA分别达到0.838 1、0.892 8、0.916 9，相比于基线U-Net分别提高0.019、0.016 8、0.023 2，推理速度为40.02?FPS能够满足工程应用的需求。在开源的Crack500数据集中验证了该模型相比于U-Net、DeepLabV3+等网络模型具有更强的性能和泛化能力。

关键词: 计算机应用, 路面裂缝检测, 深度学习, 特征融合, 语义分割