Intelligent recognition of erosion damage to concrete based on improved YOLO-v3

被引：40

作者：

Cui, Xiaoning ^{[1
]}

Wang, Qicai ^{[1
,2
]}

Dai, Jinpeng ^{[1
,2
]}

Zhang, Rongling ^{[1
,2
]}

Li, Sheng ^{[1
,2
]}

机构：

[1] Lanzhou Jiaotong Univ, Sch Civil Engn, Lanzhou 730070, Peoples R China

[2] Natl & Prov Joint Engn Lab Rd & Bridge Disaster P, Lanzhou 730070, Peoples R China

来源：

MATERIALS LETTERS | 2021年 / 302卷

关键词：

Erosion damage to concrete; Artificial intelligence; Object detection; Surfaces; Improved YOLO-V3; Deep learning;

D O I：

10.1016/j.matlet.2021.130363

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Concrete is one of the most common building materials in civil engineering. Buildings in Northwest China are facing strong wind erosion. Due to wind erosion, the surface of concrete peels off and erosion damage occurs, which has a very adverse impact on both the appearance of buildings and their safe use. Therefore, it is of great significance to carry out an intelligent identification of the erosion area of concrete. A deep learning dataset was established through a concrete erosion test to realize accurate recognition of erosion damage to concrete, and an improved YOLO-v3 algorithm model was proposed. Compared with other mainstream target detection algorithms, the improved version of YOLO-v3 is found to be able to achieve more accurate concrete erosion damage recognition, and the accuracy, precision, and map of the algorithm are 96.32%, 95.68%, and 75.68%, respectively, which verifies the applicability of deep learning to the research of concrete erosion damage.

引用

页数：4

共 13 条

[1] Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing [J].

Bhatt, Anant R. ;

Ganatra, Amit ;

Kotecha, Ketan .

PEERJ COMPUTER SCIENCE, 2021, PeerJ Inc. (07) :1-18

[2] Classification and quantification of cracks in concrete structures using deep learning image-based techniques [J].

Flah, Majdi ;

Suleiman, Ahmed R. ;

Nehdi, Moncef L. .

CEMENT & CONCRETE COMPOSITES, 2020, 114

[3] A deep-learning-based approach for fast and robust steel surface defects classification [J].

Fu, Guizhong ;

Sun, Peize ;

Zhu, Wenbin ;

Yang, Jiangxin ;

Cao, Yanlong ;

Yang, Michael Ying ;

Cao, Yanpeng .

OPTICS AND LASERS IN ENGINEERING, 2019, 121 :397-405

[4]

Garg D., 2018, 2018 IEEE PUN, P1

[5] Automatic recognition of surface defects for hot-rolled steel strip based on deep attention residual convolutional neural network [J].

Huang, Zheng ;

Wu, Jiajun ;

Xie, Feng .

MATERIALS LETTERS, 2021, 293

[6] Focal Loss for Dense Object Detection [J].

Lin, Tsung-Yi ;

Goyal, Priya ;

Girshick, Ross ;

He, Kaiming ;

Dollar, Piotr .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2999-3007

[7] SSD: Single Shot MultiBox Detector [J].

Liu, Wei ;

Anguelov, Dragomir ;

Erhan, Dumitru ;

Szegedy, Christian ;

Reed, Scott ;

Fu, Cheng-Yang ;

Berg, Alexander C. .

COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 :21-37

[8]

Redmon J, 2018, Arxiv, DOI arXiv:1804.02767

[9] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].

Ren, Shaoqing ;

He, Kaiming ;

Girshick, Ross ;

Sun, Jian .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149

[10]

Selvaraju RR, 2020, INT J COMPUT VISION, V128, P336, DOI [10.1109/ICCV.2017.74, 10.1007/s11263-019-01228-7]

← 1 2 →