干旱区生态环境知识资源中心(Arid): High-resolution concrete damage image synthesis using conditional generative adversarial network

Arid

DOI	10.1016/j.autcon.2022.104739
	High-resolution concrete damage image synthesis using conditional generative adversarial network
	Li, Shengyuan; Zhao, Xuefeng
通讯作者	Li, SY
来源期刊	AUTOMATION IN CONSTRUCTION
ISSN	0926-5805
EISSN	1872-7891
出版年	2023
卷号	147
英文摘要	Concrete damage images are essential for training deep learning-based damage detection networks. Considering the manual collection of concrete damage images is time-consuming and labor-intensive, this study proposes a synthesis method for high-resolution concrete damage images using a conditional generative adversarial network (CGAN). To this end, pix2pix, CycleGAN, OASIS, and pix2pixHD with various hyperparameters were trained and tested on 500 concrete crack and spalling images. The test results show that the trained pix2pixHD with lambda pix2pixHD = 15 is the best CGAN for concrete damage image synthesis. Concrete damage images were synthesized by the best CGAN according to hand-painted damage maps and used to train deep learning networks. The results show that the synthesized images have excellent authenticity and can be used to train and test deep learning -based concrete damage detection networks. The proposed method can be enhanced by adding damage images to the existing database or employing a better CGAN generator.
英文关键词	Concrete damage High -resolution image synthesis Conditional generative adversarial network Deep learning
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000919130200001
WOS关键词	CRACK DETECTION ; SEGMENTATION ; INSPECTION
WOS类目	Construction & Building Technology ; Engineering, Civil
WOS研究方向	Construction & Building Technology ; Engineering
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/395527
推荐引用方式 GB/T 7714	Li, Shengyuan,Zhao, Xuefeng. High-resolution concrete damage image synthesis using conditional generative adversarial network[J],2023,147.
APA	Li, Shengyuan,&Zhao, Xuefeng.(2023).High-resolution concrete damage image synthesis using conditional generative adversarial network.AUTOMATION IN CONSTRUCTION,147.
MLA	Li, Shengyuan,et al."High-resolution concrete damage image synthesis using conditional generative adversarial network".AUTOMATION IN CONSTRUCTION 147(2023).