Lightweight Improvement of a Road Defect Detection Model Based on YOLOv8
Main Article Content
Abstract
Road-defect inspection based on vehicle-mounted optical imaging requires the image-analysis model to operate under limited on-board storage and computation. This study develops a lightweight target detector for the computational interpretation stage of a visible-spectrum pavement sensing system. In the actual implementation, the original YOLOv8s backbone is replaced with a ShuffleNetV2 feature extractor, while the SPPF module, multi-scale feature-fusion neck, and detection head are retained. The ShuffleNetV2 backbone uses channel splitting, depthwise convolution, pointwise convolution, and channel shuffle to reduce redundant computation. The model is trained for 200 epochs on a seven-class road-defect dataset containing transverse patches, longitudinal patches, transverse cracks, longitudinal cracks, alligator cracks, manhole covers, and potholes. Code-level reconstruction gives 7,327,393 parameters for the improved seven-class model, and the saved best checkpoint is approximately 15 MB. The best recorded validation performance is mAP@0.5 = 0.533 and mAP@0.5:0.95 = 0.340. Compared with the original YOLOv8s result reported in this study, the lightweight model reduces model complexity but also exhibits a non-negligible decrease in detection accuracy. The results therefore demonstrate an explicit accuracy-complexity trade-off rather than accuracy-preserving compression.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
N. Ma, X. Zhang, H. T. Zheng, et al., “ShuffleNet V2: Practical guidelines for efficient CNN architecture design,” Proceedings of the European Conference on Computer Vision (ECCV) 2018, pp. 116–131.
Y. Chen, et al., “YOLO V8 Network Lightweight Method Based on Pruning and Quantization,” Journal of Advances in Applied Mathematics, 2024.
Y. Cheng, et al., “YOLO V8 Network Lightweight Method Based on Pruning and Quantization,” International Conference on Computer Science and Artificial Intelligence 2024.
H. Gan, et al., “PKD-YOLOv8: A Collaborative Pruning and Knowledge Distillation Framework for Lightweight Rapeseed Pest Detection,” Sensors, vol. 25, no. 16, Art. no. 5004, 2025.
M. Kortmann, et al., “Fast road defect detection using an improved faster R-CNN,” International Conference on Computer Vision and Pattern Recognition Workshops 2023.
J. N. Opara, et al., “Road defect detection using deep learning: A survey,” IEEE Access, vol. 11, pp. 109582–109607, 2023.
H. Wang, et al., “YOLOv8-D-CBAM: Improved YOLOv8 for pavement crack detection,” Sensors, vol. 24, no. 21, Art. no. 6783, 2024.
F. Wan, et al., “YOLO-LRDD: A lightweight road defect detection algorithm,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 8, pp. 8921–8932, 2023.
Y. Xu, et al., “YOLOv5-PD: An improved YOLOv5 algorithm for asphalt pavement defect detection,” Measurement, vol. 235, Art. no. 114785, 2024.
L. Zhang, et al., “Deep Learning-Based Algorithm for Road Defect Detection,” Sensors, vol. 25, no. 5, Art. no. 1287, 2025.
C. Wu, M. Ye, J. Zhang, and Y. Ma, “YOLO-LWNet: A lightweight road damage object detection network for mobile terminal devices,” Sensors, vol. 23, no. 6, Art. no. 3268, 2023.
J. Chen, X. Yu, Q. Li, W. Wang, et al., “LAG-YOLO: Efficient road damage detector via lightweight attention ghost module,” Journal of Intelligent Construction, vol. 2, no. 1, Art. no. 9180032, 2024.
A. Yu, Y. Gao, Y. Xiong, W. Liu, and J. She, “Mobile-YOLO: A lightweight YOLO for road crack detection on mobile devices,” Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 29, no. 6, pp. 1443–1454, 2025.
P. Huang, S. Wang, J. Chen, W. Li, and X. Peng, “Lightweight model for pavement defect detection based on improved YOLOv7,” Sensors, vol. 23, no. 16, Art. no. 7112, 2023.
W. Wang and W. Yu, “Enhancing real-time road object detection: The RD-YOLO algorithm with higher precision and efficiency,” IEEE Access, vol. 12, pp. 190876–190888, 2024.
Z. Zhang, H. Zhang, and T. Zhang, “Enhanced YOLOv8-based pavement crack detection: A high-precision approach,” PLoS One, vol. 20, no. 5, Art. no. e0324512, 2025.
S. Zhang, Z. Bei, T. Ling, Q. Chen, and L. Zhang, “Research on high-precision recognition model for multiscene asphalt pavement distresses based on deep learning,” Scientific Reports, vol. 14, Art. no. 27173, 2024.