Abstract
The frequent utilization of land transportation systems has led to the further deterioration of roads and caused traffic hazards. Early detection of asphalt pavement distresses has a necessary role in eliminating these hazards. Implementing an efficient automated method for detecting, locating, and classifying pavement distresses could help to address this problem in its early phase. This automated system has the potential to assist governments in maintaining road conditions effectively, especially those that aim to build smart cities. Furthermore, smart cars equipped with sensors and cameras can further contribute to road conditions and pavement distress inspection. The YOLO algorithm has demonstrated its potential to automate the detection process with real-time object detection and has shown promising results to be integrated into smart cars. The primary focus of this paper was to compare the performance of YOLOv4 and YOLOv5 in detecting thin and small crack objects using two publicly available image datasets, EdmCrack600 and RDD2022. Our comparisons were based not only on the architectures themselves but also on the number of classes in datasets that represent various types of pavement cracks. Additionally, we introduced an augmentation technique that is specific to crack objects in order to address the imbalanced class representation in the EdmCrack600 dataset. This technique improved final results by 11.2%. Overall, our comparisons indicated that YOLOv5 demonstrated better accuracy by achieving a mean average precision (mAP) of 65.6% on the RDD2022 dataset, and a mAP of 42.3% on the EdmCrack600 dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pais, J.C., Amorim, S.I.R., Minhoto, M.J.C.: Impact of traffic overload on road pavement performance. J. Transport. Eng. 139, 9 (2013)
Qiao, Y., Flintsch, G.W., Dawson, A.R., Parry, T.: Examining effects of climatic factors on flexible pavement performance and service life. Transp. Res. Rec. 2349, 100–107 (2013)
World Health Organization. Global status report on road safety: time for action. In: Violence, Injury Prevention, and World Health Organization. World Health Organization (2009)
Varadharajan, S., Jose, S., Sharma, K., Wander, L., Mertz, C.: Vision for road inspection. In: IEEE winter conference on applications of computer vision, pp. 115–122. IEEE (2014)
Yu, J.-M., Lee, C., Chen, L.-L.: Survival model-based economic evaluation of preventive maintenance practice on asphalt pavement. J. South China Univ. Technol. 40(11), 133–137 (2012)
Arena, F., Pau, G., Severino, A.: An overview on the current status and future perspectives of smart cars. Infrastructures 5(7), 53 (2020)
Huval, B., et al.: An empirical evaluation of deep learning on highway driving. arXiv preprint arXiv:1504.01716 (2015)
Sattar, D., Thomas, R.J., Maguire, M.: Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr. Build. Mater. 186, 1031–1045 (2018)
Klette, R.: Concise Computer Vision: An Introduction into Theory and Algorithms, vol. 233. Springer, London (2014)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Liu, W., et al.: SSD: single shot multiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Alexey, B., Wang, C.-Y., Mark Liao, H.-Y.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Jocher, G., Chaurasia, A., Stoken, A., Borovec, J.: NanoCode012. In: Kwon, Y., et al. ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation (v7.0). Zenodo (2022). https://doi.org/10.5281/zenodo.7347926
Hacıefendioğlu, K., Basri Başağa, H.: Concrete road crack detection using deep learning-based faster R-CNN method. Iranian J. Sci. Technol. Trans. Civil Eng. 1–13 (2022)
Xu, X., et al.: Crack detection and comparison study based on faster R-CNN and mask R-CNN. Sensors 22(3), 1215 (2022)
Wang, C., Mark Liao, H., Wu, Y., Chen, P., Hsieh, J., Yeh, I.: Cspnet: a new backbone that can enhance learning capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1571–1580 (2020)
Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv preprint arXiv:1710.05941 (2017)
Zhang, Y., Huang, J., Cai, F.: On bridge surface crack detection based on an improved YOLO v3 algorithm. IFAC-PapersOnLine 53(2) (2020)
Li, L., Fang, B., Zhu, J.: Performance analysis of the YOLOv4 algorithm for pavement damage image detection with different embedding positions of CBAM modules. Appl. Sci. 12(19), 10180 (2022)
Liu, Z., Wu, W., Gu, X., Li, S., Wang, L., Zhang, T.: Application of combining YOLO models and 3D GPR images in road detection and maintenance. Remote Sens. 13(6), 1081 (2021)
Yao, G., Sun, Y., Wong, M., Lv, X.: A real-time detection method for concrete surface cracks based on improved YOLOv4. Symmetry 13(9), 1716 (2021)
Yao, G., Sun, Y., Yang, Y., Liao, G.: Lightweight neural network for real-time crack detection on concrete surface in fog. Front. Mater. 8 (2021)
Wan, F., Sun, C., He, H., Lei, G., Xu, L., Xiao, T.: YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s. EURASIP J. Adv. Signal Process. 2022(1) (2022)
Teng, S., Liu, Z., Chen, G., Cheng, L.: Concrete crack detection based on well-known feature extractor model and the YOLO_v2 network. Appl. Sci. 11(2) (2021)
Mandal, V., Mussah, A.R., Adu-Gyamfi, Y.: Deep learning frameworks for pavement distress classification: a comparative analysis. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 5577–5583. IEEE (2020)
Qiu, Q., Lau, D.: Real-time detection of cracks in tiled sidewalks using YOLO-based method applied to unmanned aerial vehicle (UAV) images. Autom. Constr. 147, 104745 (2023)
Mei, Q., Gül, M., Azim, M.R.: Densely connected deep neural network considering connectivity of pixels for automatic crack detection. Autom. Constr. 110, 103018 (2020)
Mei, Q., Gül, M.: A cost effective solution for pavement crack inspection using cameras and deep neural networks. Constr. Build. Mater. 256, 119397 (2020)
Mei, Q., Gül, M., Shirzad-Ghaleroudkhani, N.: Towards smart cities: crowdsensing-based monitoring of transportation infrastructure using moving vehicles. J. Civil Struct. Health Monitor. (2020)
Tzutalin. LabelImg (2015). https://github.com/tzutalin/labelImg. Accessed 15 Dec 2022
Deeksha, A., Maeda, H., Ghosh, S.K., Toshniwal, D., Sekimoto, Y.: RDD2022: a multi-national image dataset for automatic road damage detection. arXiv preprint arXiv:2209.08538 (2022)
Zhu, H., Wei, H., Li, B., Yuan, X., Kehtarnavaz, N.: A review of video object detection: datasets, metrics and methods. Appl. Sci. 10(21), 7834 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fatali, R., Safarli, G., El Zant, S., Amhaz, R. (2023). A Comparative Study of YOLO V4 and V5 Architectures on Pavement Cracks Using Region-Based Detection. In: Collet, P., Gardashova, L., El Zant, S., Abdulkarimova, U. (eds) Complex Computational Ecosystems. CCE 2023. Lecture Notes in Computer Science, vol 13927. Springer, Cham. https://doi.org/10.1007/978-3-031-44355-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-44355-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44354-1
Online ISBN: 978-3-031-44355-8
eBook Packages: Computer ScienceComputer Science (R0)