LANA-YOLO: Road defect detection algorithm optimized for embedded solutions

Paweł TOMIŁO

doi:10.35784/acs_6692

Open full text

PDF

Published: Mar 31, 2025

DOI: https://doi.org/10.35784/acs_6692

DOI

https://doi.org/10.35784/acs_6692

Authors

Paweł TOMIŁO

p.tomilo@pollub.pl

Lublin University of Technology, Faculty of Management

https://orcid.org/0000-0003-4461-3194

Abstract

Poor pavement condition leads to increased risk of accidents, vehicle damage, and reduced transportation efficiency. The author points out that traditional methods of monitoring road conditions are time-consuming and costly, so a modern approach based on the use of developed neural network model is presented. The main aim of this paper is to create a model that can infer in real time, with less computing power and maintaining or improving the metrics of the base model, YOLOv8. Based on this assumption, the architecture of the LANA-YOLOv8 (Large Kernel Attention Involution Asymptotic Feature Pyramid) is proposed. The model's architecture is tailored to operate in environments with limited resources, including single-board minicomputers. In addition, the article presents Basic Involution Block (BIB) that uses the involution layer to provide better performance at a lower cost than convolution layers. The model was compared with other architectures on a public dataset as well as on a dataset specially created for these purposes. The developed solution has lower computing power requirements, which translates into faster inference times. At the same time, the developed model achieved better results in validation tests against the base model.

Keywords:

artificial neural network, limited resources inference, road defect detection, embedded device

References

Akyon, F. C., Altinuc, S. O., & Temizel, A. (2022). Slicing aided hyper inference and fine-tuning for small object detection. International Conference on Image Processing (ICIP) (pp. 966–970). IEEE. https://doi.org/10.1109/ICIP46576.2022.9897990

Arya, D., Maeda, H., Ghosh, S. K., Toshniwal, D., Omata, H., Kashiyama, T., & Sekimoto, Y. (2022). Crowdsensing-based road damage detection challenge (CRDDC’2022). 2022 IEEE International Conference on Big Data (Big Data) (pp. 6378–6386). IEEE. https://doi.org/10.1109/BIGDATA55660.2022.10021040

Arya, D., Maeda, H., Kumar Ghosh, S., Toshniwal, D., Omata, H., Kashiyama, T., & Sekimoto, Y. (2020). Global road damage detection: State-of-the-art solutions. 2020 IEEE International Conference on Big Data (Big Data) (pp. 5533–5539). IEEE. https://doi.org/10.1109/BIGDATA50022.2020.9377790

Bai, R., Shen, F., Wang, M., Lu, J., & Zhang, Z. (2023). Improving detection capabilities of YOLOv8-n for small objects in remote sensing imagery: Towards better precision with simplified model complexity. https://doi.org/10.21203/RS.3.RS-3085871/V1

Bhattacharya, S., Jha, H., & Nanda, R. P. (2022). Application of IoT and artificial intelligence in road safety. 2022 International Conference on Interdisciplinary Research in Technology and Management (IRTM) (pp. 1-6). IEEE. https://doi.org/10.1109/IRTM54583.2022.9791529

cvat-ai / cvat. (2025, March 21). Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale. GitHub. Retrieved September 24, 2024 from https://github.com/cvat-ai/cvat

Fu, R., Hu, Q., Dong, X., Guo, Y., Gao, Y., & Li, B. (2020). Axiom-based Grad-CAM: Towards accurate visualization and explanation of CNNs. ArXiv, abs/2008.02312v4. https://arxiv.org/abs/2008.02312v4

Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020). GhostNet: More features from cheap operations. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 1577–1586). IEEE. https://doi.org/10.1109/CVPR42600.2020.00165

Jakobsen, M. D., Glies Vincents Seeberg, K., Møller, M., Kines, P., Jørgensen, P., Malchow-Møller, L., Andersen, A. B., & Andersen, L. L. (2023). Influence of occupational risk factors for road traffic crashes among professional drivers: Systematic review. Transport Reviews, 43(3), 533–563. https://doi.org/10.1080/01441647.2022.2132314

Jiang, Y. (2024). Road damage detection and classification using deep neural networks. Discover Applied Sciences, 6, 421. https://doi.org/10.1007/s42452-024-06129-0

Li, D., Hu, J., Wang, C., Li, X., She, Q., Zhu, L., Zhang, T., & Chen, Q. (2021). Involution: Inverting the inherence of convolution for visual recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 12316–12325). IEEE. https://doi.org/10.1109/CVPR46437.2021.01214

Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., & Ren, Q. (2024). Slim-neck by GSConv: a lightweight-design for real-time detector architectures. Journal of Real-Time Image Processing, 21, 62. https://doi.org/10.1007/S11554-024-01436-6

Li, Y., Hou, Q., Zheng, Z., Cheng, M. M., Yang, J., & Li, X. (2023). Large selective kernel network for remote sensing object detection. IEEE International Conference on Computer Vision (pp. 16748–16759). IEEE. https://doi.org/10.1109/ICCV51070.2023.01540

Liu, G., Reda, F. A., Shih, K. J., Wang, T.-C., Tao, A., & Catanzaro, B. (2018). Image inpainting for irregular holes using partial convolutions. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Computer Vision – ECCV 2018 (Vol. 11215, pp. 89–105). Springer International Publishing. https://doi.org/10.1007/978-3-030-01252-6_6

Liu, J., Zhang, S., Ma, Z., Zeng, Y., & Liu, X. (2023). A workpiece-dense scene object detection method based on improved YOLOv5. Electronics, 12(13), 2966. https://doi.org/10.3390/ELECTRONICS12132966

Liu, Q., Huang, W., Duan, X., Wei, J., Hu, T., Yu, J., Huang, J., Liu, Q., Huang, W., Duan, X., Wei, J., Hu, T., Yu, J., & Huang, J. (2023). DSW-YOLOv8n: A new underwater target detection algorithm based on improved YOLOv8n. Electronics, 12(18), 3892. https://doi.org/10.3390/ELECTRONICS12183892

Liu, S., Huang, D., & Wang, Y. (2019). Learning spatial fusion for single-shot object detection. ArXiv, abs/1911.09516v2. https://arxiv.org/abs/1911.09516v2

Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., & Huang, Z. (2023). Efficient multi-scale attention module with cross-spatial learning. IEEE International Conference on Acoustics, Speech and Signal Processing – Proceedings (ICASSP) (pp. 1-5). IEEE. https://doi.org/10.1109/ICASSP49357.2023.10096516

Ranyal, E., Sadhu, A., & Jain, K. (2022). Road condition monitoring using smart sensing and artificial intelligence: A review. Sensors, 22(8), 3044. https://doi.org/10.3390/S22083044

Tang, Z., Chamchong, R., & Pawara, P. (2023). A comparison of road damage detection based on YOLOv8. International Conference on Machine Learning and Cybernetics (pp. 223–228). IEEE. https://doi.org/10.1109/ICMLC58545.2023.10327993

Tomiło, P. (2024, October 1). CoCG Road Condition - Detection Dataset (CoCGRCDD). Mendeley Data. https://doi.org/10.17632/SNYYFKNW56.1

Tomiło, P., Oleszczuk, P., Laskowska, A., Wilczewska, W., & Gnapowski, E. (2024). Effect of architecture and inferencep of artificial neural network models in the detection task on energy demand. Energies, 17(21), 5417. https://doi.org/10.3390/EN17215417

Wang, J., Meng, R., Huang, Y., Zhou, L., Huo, L., Qiao, Z., & Niu, C. (2024). Road defect detection based on improved YOLOv8s model. Scientific Reports, 14, 16758. https://doi.org/10.1038/s41598-024-67953-3

Wang, X., Gao, H., Jia, Z., & Li, Z. (2023). BL-YOLOv8: An improved road defect detection model based on YOLOv8. Sensors, 23(20), 8361. https://doi.org/10.3390/S23208361

Xing, Y., Han, X., Pan, X., An, D., Liu, W., & Bai, Y. (2024). EMG-YOLO: road crack detection algorithm for edge computing devices. Frontiers in Neurorobotics, 18, 1423738. https://doi.org/10.3389/FNBOT.2024.1423738

Xu, H. (2022). FCD-YOLO: Improved YOLOv5 based on decoupled head and attention mechanism for defect detection on printed circuit board. 2022 2nd International Conference on Networking Systems of AI (INSAI) (pp. 7–11). IEEE. https://doi.org/10.1109/INSAI56792.2022.00011

Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., & Liang, R. (2023). AFPN: Asymptotic feature pyramid network for object detection. IEEE International Conference on Systems, Man and Cybernetics (pp. 2184–2189). IEEE. https://doi.org/10.1109/SMC53992.2023.10394415

Zhou, Y., & Yang, K. (2022). Exploring TensorRT to improve real-time inference for deep learning. 2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) (pp. 2011–2018). IEEE. https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys57074.2022.00299

Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. ArXiv, abs/2010.04159v4. https://arxiv.org/abs/2010.04159v4

TOMIŁO, P. (2025). LANA-YOLO: Road defect detection algorithm optimized for embedded solutions. Applied Computer Science, 21(1), 164–181. https://doi.org/10.35784/acs_6692

Article Sidebar

Main Article Content

DOI

Authors

Abstract

Keywords:

References

Article Details

License