Crack-Detection Method for Asphalt Pavement Based on the Improved YOLOv5
Publication: Journal of Performance of Constructed Facilities
Volume 38, Issue 2
Abstract
In view of the low identification accuracy of the crack-detection technology of asphalt pavement under the current conditions of complex pavement (subject to strong light, water on the road, debris, and so on), an asphalt pavement crack-detection algorithm based on improved YOLOv5s was proposed by building the data set for asphalt pavement cracks. The first step was to make the following improvements to the original YOLOv5s model according to the characteristics of the asphalt pavement crack data set: The -means++ algorithm was used to recluster the anchor points of the crack data set, and the initial anchor frame matching the crack characteristics of the asphalt pavement was obtained to replace the default initial anchor frame in the YOLOv5 original model. In the prediction part of the original model, the Convolutional Block Attention Module (CBAM) was added in the order of first channel and then space to improve the detection ability of the model to small cracks. The CIoU_Loss function was used as the regression loss function of the model to replace the GIoU_Loss function in the original model to improve the positioning accuracy of the anchor frame. The second step was to perform an ablation experiment on the improved YOLOv5s model. This would prove that each improvement scheme could increase detection ability without conflict. The final step was to compare the improved YOLOv5s model with various classic target detection models in the data set of this paper: the Crack Forest Data set (CFD), the Crack500 data set, and the Crack200 data set. The results showed that the detection of the improved YOLOv5s model on each data set was better than other target detection models. The [email protected] and mAP@[0.5:0.95] of this model on the data set of this paper were 90.58% and 56.08%, respectively, which were much higher than other target detection models. These findings indicate that the improved YOLOv5s model had better detection under complex pavement conditions and could provide a theoretical basis for the automatic detection of asphalt pavement cracks.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This research was supported by the National Natural Science Foundation of China (Grant No. 51808327) and Natural Science Foundation of Shandong Province (Grant No. ZR2019PEE016).
References
Ali, L., F. Alnajjar, M. M. A. Parambil, M. I. Younes, Z. I. Abdelhalim, and H. Aljassmi. 2022. “Development of YOLOv5-based real-time smart monitoring system for increasing lab safety awareness in educational institutions.” Sensors 22 (22): 8820. https://doi.org/10.3390/s22228820.
Cao, J., Y. Kong, X. Zhang, Y. Li, and X. Xie. 2020. “Target detection algorithm based on improved multi-scale SSD.” J. Phys.: Conf. Ser. 1570 (1): 012014. https://doi.org/10.1088/1742-6596/1570/1/012014.
Cao, Y., and J. Xu. 2023. “DV-Hop-based localization algorithm using optimum anchor nodes subsets for wireless sensor network.” Ad Hoc Networks 139 (Feb): 103035. https://doi.org/10.1016/j.adhoc.2022.103035.
Dang, X. 2021. “Application of 3D laser scanning technology in monitoring deformation of port trail.” IOP Conf. Ser.: Earth Environ. Sci. 782 (1): 012151. https://doi.org/10.1088/1755-1315/783/1/012151.
Gao, C., J. Wu, H. Yu, J. Yin, and S. Guo. 2022a. “FIRN: A novel fish individual recognition method with accurate detection and attention mechanism.” Electronics 11 (21): 3459. https://doi.org/10.3390/electronics11213459.
Gao, J., S. Dai, J. Huang, X. Xiao, L. Liu, L. Wang, X. Sun, Y. Guo, and M. Li. 2022b. “Kiwifruit detection method in orchard via an improved light-weight YOLOv4.” Agronomy 12 (9): 2081. https://doi.org/10.3390/agronomy12092081.
Han, Z., H. Chen, Y. Liu, Y. Li, Y. Du, and H. Zhang. 2021. “Vision-based crack detection of asphalt pavement using deep convolutional neural network.” Iran. J. Sci. Technol.-Trans. Civ. Eng. 45 (3): 2047–2055. https://doi.org/10.1007/s40996-021-00668-x.
Hao, Q., X. Guo, and F. Yang. 2023. “Fast recognition method for multiple apple targets in complex occlusion environment based on improved YOLOv5.” J. Sensors (Feb): 2023. https://doi.org/10.1155/2023/3609541.
Highway Technical Status Assessment Standard. 2018. Standard for evaluation of highway technical conditions. JTG 5210-2018. Beijing: Standard Press of China.
Hu, G. X., B. L. Hu, Z. Yang, L. Huang, and P. Li. 2021. “Pavement crack detection method based on deep learning models.” Wireless Commun. Mobile Comput. 2021 (May): 1–13.
Hu, W., J. Xiong, J. Liang, Z. Xie, Z. Liu, Q. Huang, and Z. Yang. 2023. “A method of citrus epidermis defects detection based on an improved YOLOv5.” Biosyst. Eng. 227 (Mar): 19–35. https://doi.org/10.1016/j.biosystemseng.2023.01.018.
Huang, Z., X. Jiang, F. Wu, Y. Fu, Y. Zhang, T. Fu, and J. Pei. 2023. “An improved method for ship target detection based on YOLOv4.” Appl. Sci. 13 (3): 1302. https://doi.org/10.3390/app13031302.
Jocher, B. M., J. D. Schilling, I. Fischer, T. Nakajima, F. Wan, Y. Tanaka, G. A. Ewald, K. Kutkar, M. Masood, and A. Itoh. 2020. “Incidence and risk factors for acute kidney injury post-heart transplant: An analysis of peri-operative hemodynamics.” J. Heart Lung Transplant. 39 (4): 290.
Kasper-Eulaers, M., N. Hahn, S. Berger, T. Sebulonsen, Ø. Myrland, and P. E. Kummervold. 2021. “Detecting heavy goods vehicles in rest areas in winter conditions using YOLOv5.” Algorithms 14 (4): 114. https://doi.org/10.3390/a14040114.
Krishnadas, P., K. Chadaga, N. Sampathila, S. Rao, and S. Prabhu. 2022. “Classification of malaria using object detection models.” Informatics 9 (4): 76. https://doi.org/10.3390/informatics9040076.
Kumar, S., R. Ahmed, S. Bharany, M. Shuaib, T. Ahmad, E. Tag Eldin, A. U. Rehman, and M. Shafiq. 2022. “Exploitation of machine learning algorithms for detecting financial crimes based on customers’ behavior.” Sustainability 14 (21): 13875. https://doi.org/10.3390/su142113875.
Lakomski, M., G. Tosik, and P. Niedzielski. 2021. “Optical fiber sensor for PVC sheet piles monitoring.” Electronics 10 (13): 1604. https://doi.org/10.3390/electronics10131604.
Li, M., G. Sun, and J. Yu. 2023. “A pedestrian detection network model based on improved YOLOv5.” Entropy 25 (2): 381. https://doi.org/10.3390/e25020381.
Li, W., J. Liu, and H. Mei. 2022. “Lightweight convolutional neural network for aircraft small target real-time detection in airport videos in complex scenes.” Sci. Rep. 12 (1): 14474. https://doi.org/10.1038/s41598-022-18263-z.
Liang, H., T. Wu, Q. Zhang, and H. Zhou. 2022. “Non-maximum suppression performs later in multi-object tracking.” Appl. Sci. 12 (7): 3334. https://doi.org/10.3390/app12073334.
Ma, R., J. Wang, W. Zhao, H. Guo, D. Dai, Y. Yun, L. Li, F. Hao, J. Bai, and D. Ma. 2022. “Identification of maize seed varieties using MobileNetV2 with improved attention mechanism CBAM.” Agriculture 13 (1): 11. https://doi.org/10.3390/agriculture13010011.
Ma, Y., and W. Cheng. 2020. “Optimization and parallelization of fuzzy clustering algorithm based on the improved kmeans++ clustering.” IOP Conf. Ser.: Mater. Sci. Eng. 768 (7): 072106. https://doi.org/10.1088/1757-899X/768/7/072106.
Mukhopadhyay, A., P. Biswas, A. Agarwal, and I. Mukherjee. 2019. “Performance comparison of different CNN models for Indian road dataset.” In Proc., 3rd Int. Conf. on Graphics and Signal Processing, 29–33. New York: Association for Computing Machinery.
Nguyen, N. H. T., S. Perry, D. Bone, H. T. Le, and T. T. Nguyen. 2021. “Two-stage convolutional neural network for road crack detection and segmentation.” Expert Syst. Appl. 186 (Dec): 115718. https://doi.org/10.1016/j.eswa.2021.115718.
Niu, H., X. Hu, and H. Li. 2021. “Improved YOLOv5 network-based object detection for anti-intrusion of gantry crane.” In Proc., 2021 2nd Int. Conf. on Control, Robotics and Intelligent System, 147–152. New York: Association for Computing Machinery.
Othmani, M. 2022. “A vehicle detection and tracking method for traffic video based on faster R-CNN.” Multimedia Tools Appl. 81 (20): 28347–28365. https://doi.org/10.1007/s11042-022-12715-4.
Parveen, R., and N. S. Varma. 2021. “Friend’s recommendation on social media using different algorithms of machine learning.” Global Transitions Proc. 2 (2): 273–281. https://doi.org/10.1016/j.gltp.2021.08.012.
Sekar, A., and V. Perumal. 2021. “Automatic road crack detection and classification using multi-tasking faster RCNN.” J. Intell. Fuzzy Syst. Appl. Eng. Technol. 41 (6): 6615–6628. https://doi.org/10.3233/JIFS-210475.
Sha, G., J. Wu, and B. Yu. 2022. “The improved faster-RCNN for spinal fracture lesions detection.” J. Intell. Fuzzy Syst. 42 (6): 5823–5837. https://doi.org/10.3233/JIFS-212389.
Shi, Y., L. Cui, Z. Qi, F. Meng, and Z. Chen. 2016. “Automatic road crack detection using random structured forests.” IEEE Trans. Intell. Transp. Syst. 17 (12): 3434–3445. https://doi.org/10.1109/TITS.2016.2552248.
Shu, Z., Z. Yan, and X. Xu. 2021. “Pavement crack detection method of street view images based on deep learning.” J. Phys. Conf. Ser. 1952 (2): 022043. https://doi.org/10.1088/1742-6596/1952/2/022043.
Tong, C., X. Yang, Q. Huang, and F. Qian. 2022. “NGIoU loss: Generalized intersection over union loss based on a new bounding box regression.” Appl. Sci. 12 (24): 12785. https://doi.org/10.3390/app122412785.
Tran, T. S., V. P. Tran, H. J. Lee, J. M. Flores, and V. P. Le. 2022. “A two-step sequential automated crack detection and severity classification process for asphalt pavements.” Int. J. Pavement Eng. 23 (6): 2019–2033. https://doi.org/10.1080/10298436.2020.1836561.
Wang, C., Y. Liu, F. Chang, and M. Lu. 2022a. “Pedestrian detection based on YOLOv3 multimodal data fusion.” Syst. Sci. Control Eng. 10 (1): 832–845. https://doi.org/10.1080/21642583.2022.2129507.
Wang, P., H. Huang, M. Wang, and B. Li. 2021. “YOLOv5s-FCG: An improved YOLOv5 method for inspecting riders’ helmet wearing.” J. Phys.: Conf. Ser. 2024 (1): 012059. https://doi.org/10.1088/1742-6596/2024/1/012059.
Wang, X., H. Zhang, and W. Xie. 2017. “Analysis of dynamic accumulative damage about the lining structure of high speed railway’s tunnel based on ultrasonic testing technology.” IOP Conf. Ser.: Earth Environ. Sci. 81 (1): 012127. https://doi.org/10.1088/1755-1315/81/1/012127/meta.
Wang, Z., L. Wu, T. Li, and P. Shi. 2022b. “A smoke detection model based on improved YOLOv5.” Mathematics 10 (7): 1190. https://doi.org/10.3390/math10071190.
Wei, Q., H. Li, C. Luo, J. Yu, Y. Zheng, F. Wang, and B. Zhang. 2022. “Small sample and efficient crop pest recognition method based on transfer learning and data transformation.” J. Comput. Methods Sci. Eng. 22 (5): 1697–1709. https://doi.org/10.3233/JCM-226121.
Woo, S., J. Park, J. Y. Lee, and I. S. Kweon. 2018. “CBAM: Convolutional block attention module.” In Proc., European Conf. on Computer Vision (ECCV), 3–19. Cham, Switzerland: Springer.
Wu, S., X. Wang, and C. Guo. 2023. “Application of feature pyramid network and feature fusion single shot multibox detector for real-time prostate capsule detection.” Electronics 12 (4): 1060. https://doi.org/10.3390/electronics12041060.
Xu, X., M. Zhao, P. Shi, R. Ren, X. He, X. Wei, and H. Yang. 2022. “Crack detection and comparison study based on faster R-CNN and mask R-CNN.” Sensors 22 (3): 1215. https://doi.org/10.3390/s22031215.
Xue, Q., H. Lin, and F. Wang. 2022. “FCDM: An improved forest fire classification and detection model based on YOLOv5.” Forests 13 (12): 2129. https://doi.org/10.3390/f13122129.
Xue, Z., R. Xu, D. Bai, and H. Lin. 2023. “YOLO-Tea: A tea disease detection model improved by YOLOv5.” Forests 14 (2): 415. https://doi.org/10.3390/f14020415.
Yan, K., and Z. Zhang. 2021. “Automated asphalt highway pavement crack detection based on deformable single shot multi-box detector under a complex environment.” IEEE Access 9 (Nov): 150925–150938. https://doi.org/10.1109/ACCESS.2021.3125703.
Yang, F., L. Zhang, S. Yu, D. Prokhorov, X. Mei, and H. Ling. 2019. “Feature pyramid and hierarchical boosting network for pavement crack detection.” IEEE Trans. Intell. Transp. Syst. 21 (4): 1525–1535. https://doi.org/10.1109/TITS.2019.2910595.
Yu, H., X. Li, Y. Feng, and S. Han. 2022. “Multiple attentional path aggregation network for marine object detection.” Appl. Intell. 53 (2): 2434–2451. https://doi.org/10.1007/s10489-022-03622-0.
Yu, L., M. Qian, Q. Chen, F. Sun, and J. Pan. 2023. “An improved YOLOv5 model: Application to mixed impurities detection for walnut kernels.” Foods 12 (3): 624. https://doi.org/10.3390/foods12030624.
Zhang, X., Y. Li, J. Du, R. Zhao, K. Xu, L. Zhang, and Y. She. 2023. “Feature pyramid networks and long short-term memory for EEG feature map-based emotion recognition.” Sensors 23 (3): 1622. https://doi.org/10.3390/s23031622.
Zhao, B., Y. Wu, X. Guan, L. Gao, and B. Zhang. 2021. “An improved aggregated-mosaic method for the sparse object detection of remote sensing imagery.” Remote Sens. 13 (13): 2602. https://doi.org/10.3390/rs13132602.
Zhou, J., P. Jiang, A. Zou, X. Chen, and W. Hu. 2021. “Ship target detection algorithm based on improved YOLOv5.” J. Mar. Sci. Eng. 9 (8): 908. https://doi.org/10.3390/jmse9080908.
Zhou, L., X. Rao, Y. Li, X. Zou, B. Qian, and Y. Lin. 2022. “A lightweight object detection method in aerial images based on dense feature fusion path aggregation network.” ISPRS Int. J. Geo-Inf. 11 (3): 189. https://doi.org/10.3390/ijgi11030189.
Zhu, Q., S. Huang, H. Hu, H. Li, M. Chen, and R. Zhong. 2021. “Depth-enhanced feature pyramid network for occlusion-aware verification of buildings from oblique images.” ISPRS J. Photogramm. Remote Sens. 174 (Apr): 105–116. https://doi.org/10.1016/j.isprsjprs.2021.01.025.
Zou, Q., Y. Cao, Q. Li, Q. Mao, and S. Wang. 2012. “CrackTree: Automatic crack detection from pavement images.” Pattern Recognit. Lett. 33 (3): 227–238. https://doi.org/10.1016/j.patrec.2011.11.004.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 38 • Issue 2 • April 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jul 6, 2023
Accepted: Nov 22, 2023
Published online: Feb 8, 2024
Published in print: Apr 1, 2024
Discussion open until: Jul 8, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.