当前位置: X-MOL 学术Adv. Struct. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A vision-based active learning convolutional neural network model for concrete surface crack detection
Advances in Structural Engineering ( IF 2.6 ) Pub Date : 2020-06-08 , DOI: 10.1177/1369433220924792
Zhen Wang 1, 2, 3 , Guoshan Xu 1, 2, 3 , Yong Ding 1, 2, 3 , Bin Wu 4 , Guoyu Lu 5
Affiliation  

Concrete surface crack detection based on computer vision, specifically via a convolutional neural network, has drawn increasing attention for replacing manual visual inspection of bridges and buildings. This article proposes a new framework for this task and a sampling and training method based on active learning to treat class imbalances. In particular, the new framework includes a clear definition of two categories of samples, a relevant sliding window technique, data augmentation and annotation methods. The advantages of this framework are that data integrity can be ensured and a very large amount of annotation work can be saved. Training datasets generated with the proposed sampling and training method not only are representative of the original dataset but also highlight samples that are highly complex, yet informative. Based on the proposed framework and sampling and training strategy, AlexNet is re-tuned, validated, tested and compared with an existing network. The investigation revealed outstanding performances of the proposed framework in terms of the detection accuracy, precision and F1 measure due to its nonlinear learning ability, training dataset integrity and active learning strategy.

中文翻译:

一种用于混凝土表面裂纹检测的基于视觉的主动学习卷积神经网络模型

基于计算机视觉的混凝土表面裂纹检测,特别是通过卷积神经网络,在取代人工目视检查桥梁和建筑物方面引起了越来越多的关注。本文为此任务提出了一个新框架,并提出了一种基于主动学习的采样和训练方法来处理类不平衡。特别是,新框架包括对两类样本的明确定义,相关的滑动窗口技术、数据增强和注释方法。该框架的优点是可以保证数据的完整性,并且可以节省非常大量的标注工作。使用建议的采样和训练方法生成的训练数据集不仅代表原始数据集,而且突出显示高度复杂但信息丰富的样本。基于提出的框架以及采样和训练策略,AlexNet 被重新调整、验证、测试并与现有网络进行比较。调查表明,由于其非线性学习能力、训练数据集完整性和主动学习策略,所提出的框架在检测精度、精度和 F1 度量方面表现出色。
更新日期:2020-06-08
down
wechat
bug