A field application of crack diagnosis and classification technologies based on IPTs and deep-learning using UAV
This paper deals with the study of the detection and quantification of cracks in bridge structures using image data obtained by using Unmanned Aerial Vehicle(UAV).Our proposed technology includes image acquisition system using UAV,the classification system of crack based on Deep-learning and algorithms of quantification using improved Image Processing Techniques(IPTs).Performances of the technique were evaluated through the field test.The non-contact detection technology of crack on bridge can be applied to the actual bridge inspection and it is expected to increase the economic and technical efficiency.
Vision-based Classification Deep Learning Crack detection UAV
Jin-Hwan Lee Sung-Sik Yoon In-Ho Kim Hyung-Jo Jung
Ph.D Student,Department of Civil Engineering,KAIST,Daejeon,Republic of Korea Postdoctoral Researcher,Applied Science Research Institute,KAIST,Daejeon,Republic of Korea Professor,Department of Civil and Environmental Engineering,KAIST,Daejeon,Republic of Korea
国际会议
The 7th World Conference on Structural Control and Monitoring(7WCSCM)(第七届结构控制与监测世界大会)
青岛
英文
1507-1508
2018-07-22(万方平台首次上网日期,不代表论文的发表时间)