[1] Wang Yanhua, He Junze, Zhang Mingzhou, et al. Concrete crack identification in complex environments based on SSD and pruning neural network [J]. Journal of Southeast University (English Edition), 2023, 39 (4): 393-399. [doi:10.3969/j.issn.1003-7985.2023.04.008]

Copy

Concrete crack identification in complex environments based on SSD and pruning neural network()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

39

Issue:

2023 4

Page:

393-399

Research Field:

Computer Science and Engineering

Publishing date:

2023-12-20

Info

Title:

Concrete crack identification in complex environments based on SSD and pruning neural network

Author(s):

Wang Yanhua¹;  2;  He Junze¹;  2;  Zhang Mingzhou¹;  2;  Dai Bowen¹;  2;  Xu Haoran³

¹Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education, Southeast University, Nanjing 211189, China
²School of Civil Engineering, Southeast University, Nanjing 211189, China
³Chien-Shiung Wu College, Southeast University, Nanjing 211189, China

Keywords:

crack identification;  pruned neural network;  image noise addition;  antinoise performance;  disease detection

PACS:

TP391.41

DOI:

10.3969/j.issn.1003-7985.2023.04.008

Abstract:

To solve the problem of poor crack identification algorithm performance in complex environments, an improved method based on a single-shot multibox detector(SSD)algorithm was proposed. This method realized high-precision crack identification for crack images with added noise by adjusting the combination of the number of different resolution prior bounding boxes in the original SSD algorithm. A sufficient number of crack images were captured and preprocessed in actual scenes and laboratories, and noise was added to the crack dataset using a pretzel algorithm to simulate the crack images in complex environments. The improved method was tested along with the original SSD algorithm to identify the crack dataset, and their test results were compared. The results show that the crack identification accuracy of the original SSD algorithm and improved method decreases with increasing noise levels. When a 20% grade of pretzel noise is added at high density, the accuracy in recognizing cracks is 31.7% and 93.0% for the original SSD algorithm and the improved method, respectively. Therefore, the improved method has excellent antinoise ability and can be used for crack identification in complex environments.

References:

[1] Ni Y H, Lu H, Ji C, et al. Comparative analysis on bridge corrosion damage detection based on semantic segmentation[J]. Journal of Southeast University(Natural Science Edition), 2023, 53(2):201-209. DOI:10.3969/j.issn.1001-0505.2023.02.003. (in Chinese)
[2] Cheng J M, Gao Y Q, Yan H D, et al. Statistical analysis of nondestructive testing results of cast steel joints in civil engineering structures[J]. Journal of Southeast University(English Edition), 2022, 38(1):1-8. DOI: 10.3969/j.issn.1003-7985.2022.01.001.
[3] Jiang J W, Ni F J. Evaluation of fatigue property of asphalt mixtures based on digital image correlation method[J]. Journal of Southeast University(English Edition), 2017, 33(2): 216-223. DOI: 10.3969/j.issn.1003-7985.2017.02.015.
[4] Li Z J, Wang H, Wang R G, et al. Experimental study on fatigue performance of diaphragm openings of orthotropic steel bridge decks based on 3D-DIC[J]. Journal of Southeast University(Natural Science Edition), 2019, 49(6): 1116-1123. DOI:10.3969/j.issn.1001-0505.2019.06.014. (in Chinese)
[5] Ngeljaratan L, Moustafa M A. Structural health monitoring and seismic response assessment of bridge structures using target-tracking digital image correlation[J]. Engineering Structures, 2020, 213:110551. DOI:10.1016/j.engstruct.2020.110551.
[6] Zhang L, Yang F, Daniel Z Y, et al. Road crack detection using deep convolutional neural network[C]//IEEE International Conference on Image Processing(ICIP). Phoenix, AZ, USA, 2016: 3708-3712. DOI: 10.1109/ICIP.2016.7533052.
[7] Cha Y-J, Choi W, Büyüköztürk O. Deep learning-based crack damage detection using convolutional neural networks: Deep learning-based crack damage detection using CNNs[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361-378. DOI: 10.1111/mice.12263.
[8] Lang H, Wen T, Lu J, et al. 3D pavement crack detection method based on deep learning[J]. Journal of Southeast University(Natural Science Edition), 2021, 51(1): 53-60. DOI:10.3969/j.issn.1001-0505.2021.01.008. (in Chinese)
[9] Oullette R, Browne M, Hirasawa K. Genetic algorithm optimization of a convolutional neural network for autonomous crack detection[C]// Proceedings of the 2004 Congress on Evolutionary Computation. Portland, ME, USA, 2004: 516-521. DOI: 10.1109/CEC.2004.1330900.
[10] Xu J, Zhao W, Liu P, et al. Removing rain and snow in a single image using guided filter[C]// IEEE International Conference on Computer Science and Automation Engineering(CSAE). Zhangjiajie, 2012: 304-307. DOI: 10.1109/CSAE.2012.6272780.
[11] Xu J, Zhao W, Liu P, et al. An improved guidance image based method to remove rain and snow in a single image[J]. Computer and Information Science, 2012, 5(3): 49-55. DOI: 10.5539/cis.v5n3p49.
[12] Tan R T, IEEE. Visibility in bad weather from a single image[C]// The IEEE Conference on Computer Vision and Pattern identification. Anchorage, AK, USA, 2008: 1-8. DOI: 10.1109/cvpr.2008.4587643.
[13] Satrasupalli S, Daniel E, Guntur S R. Single image haze removal based on transmission map estimation using encoder-decoder based deep learning architecture[J]. Optik, 2021, 248: 168197. DOI: 10.1016/j.ijleo.2021.168197.
[14] Ling Z, Fan G, Gong J, et al. Learning deep transmission network for efficient image dehazing[J]. Multimedia Tools and Applications, 2019, 78(1): 213-236. DOI: 10.1007/s11042-018-5687-0.
[15] Yang C Q, Li S, Wang B K, et al. High anti-noise extraction and identification method for concrete cracks based on dynamic threshold[J]. Journal of Southeast University(Natural Science Edition), 2021, 51(6): 967-972. DOI:10.3969/j.issn.1001-0505.2021.06.007. (in Chinese)
[16] Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector[C]// 14th European Conference on Computer Vision(ECCV). Amsterdam, Netherlands, 2016: 21-37. DOI: 10.1007/978-3-319-46448-0_2.
[17] Azzeh J, Zahran B, Alqadi Z. Salt and pepper noise: effects and removal[J]. JOIV: International Journal on Informatics Visualization, 2018, 2(4): 252-256. DOI: 10.30630/joiv.2.4.151.
[18] Padilla R, Netto S L, Da Silva E.A.B. A survey on performance metrics for object-detection algorithms [C]// 27th International Conference on Systems, Signals and Image Processing(IWSSIP). Niteroi, Brazil, 2020: 237-242. DOI: 10.1109/IWSSIP48289.2020.9145130.
[19] Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Trans Pattern Anal Mach Intell, 2010, 32(9): 19. DOI: 10.1109/TPAMI.2009.167.
[20] Wilson A C, Roelofs R, Stern M, et al. The marginal value of adaptive gradient methods in machine learning[C]// 31st Annual Conference on Neural Information Processing Systems(NIPS). Long Beach, CA, USA, 2017:4148-4158. DOI: 10.48550/arXiv.1705.08292.
[21] Smith L N. Cyclical learning rates for training neural networks[C]// IEEE Winter Conference on Applications of Computer Vision(WACV). Santa Rosa, CA, USA, 2017: 464-472. DOI: 10.1109/wacv.2017.58.
[22] Girshick R. Fast R-CNN[C]// IEEE International Conference on Computer Vision(ICCV). Santiago, Chile, 2015: 1440-1448. DOI: 10.1109/ICCV.2015.169.
[23] Wan C, Xiong X, Wen B, et al. Crack detection for concrete bridges with imaged based deep learning[J]. Science Progress, 2022, 105(4): 1-10. DOI: 10.1177/00368504221128487.

Memo

Memo:

Biography: Wang Yanhua(1977—), female, doctor, researcher-level senior engineer, wyh00737@seu.edu.cn.
Foundation items: The National Major Scientific Research Instrument Development Project(No.11827801), the National Science and Technology Project(No.2020YFC1511904).
Citation: Wang Yanhua, He Junze, Zhang Mingzhou, et al. Concrete crack identification in complex environments based on SSD and pruning neural network[J].Journal of Southeast University(English Edition), 2023, 39(4):393-399.DOI:10.3969/j.issn.1003-7985.2023.04.008.

Common functions