Defect-Detection Model for Underground Parking Lots Using Image Object-Detection Method
作者机构:Architectural EngineeringHanyang UniversityERICAAnsan15588Korea Department of Artificial IntelligenceAjou UniversitySuwon16499Korea Division of Architecture and Civil EngineeringKangwon National UniversitySamcheok25913Korea Division of Smart Convergence EngineeringHanyang UniversityERICAAnsan15588Korea Graduate School of InformationYonsei UniversitySeoul03722Korea
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2021年第66卷第3期
页 面:2493-2507页
核心收录:
学科分类:0831[工学-生物医学工程(可授工学、理学、医学学位)] 0808[工学-电气工程] 0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 0805[工学-材料科学与工程(可授工学、理学学位)] 0701[理学-数学] 0801[工学-力学(可授工学、理学学位)] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:a grant(19CTAP-C152020-01)from Technology Advancement Research Program(TARP)funded by the Ministry of Land Infrastructure and Transport of the Korean government
主 题:Faster R-CNN deep learning defect detection concrete structures
摘 要:The demand for defect diagnoses is gradually gaining ground owing to the growing necessity to implement safe inspection methods to ensure the durability and quality of ***,conventional manpower-based inspection methods not only incur considerable cost and time,but also cause frequent disputes regarding defects owing to poor ***,the demand for an effective and efficient defect-diagnosis model for concrete structures is imminent,as the reduction in maintenance costs is significant from a long-term ***,this paper proposes a deep learning-based image objectidentification method to detect the defects of paint peeling,leakage peeling,and leakage traces that mostly occur in underground parking lots made of concrete *** deep learning-based object-detection method can replace conventional visual inspection methods.A faster region-based convolutional neural network(R-CNN)model was used with a training dataset of 6,281 images that utilized a region proposal network to objectively localize the regions of interest and detect the surface *** defects were classified according to their type,and the learning of each exclusive model was ensured through test sets obtained from real underground parking *** a result,average precision scores of 37.76%,36.42%,and 61.29%were obtained for paint peeling,leakage peeling,and leakage trace defects,***,this study verified the performance of the faster RCNN-based defect-detection algorithm along with its applicability to underground parking lots.