A Novel UAV-based Road Damage Detection Algorithm with Lightweight Convolution and Attention Mechanism

Liang Chen; Peishu Wu; Weilong Tan; Han Li; Haonan Chen; Nianyin Zeng

doi:10.53941/ijndi.2025.100025

Abstract

In this paper, a novel attention- and lightweight convolution-based road damage detection network (ALC-Net) is proposed to address the trade-off between accuracy and real-time performance in processing unmanned aerial vehicle (UAV) imagery. Specifically, a lightweight module that integrates ghost convolution with the squeeze-and-excitation (SE) attention mechanism is designed, which effectively reduces model parameters while enhancing detection accuracy. The focus module is introduced to perform downsampling and channel-wise concatenation of input images, thereby enriching feature diversity. Furthermore, a coordinate attention mechanism is incorporated to aggregate horizontal and vertical spatial information, emphasizing subtle road damage characteristics. The proposed ALC-Net is comprehensively evaluated on a UAV-captured road damage dataset, demonstrating superior detection performance compared to other state-of-the-art approaches. The contributions of key components in ALC-Net are also validated through ablation studies, confirming their ability to enhance feature extraction capabilities while reducing computational complexity. Additionally, experiments on non-UAV road damage datasets further reveal the robust generalization capability of ALC-Net, exhibiting substantial potential for broader applications.

References

1.
Abu Dabous, S.; Ait Gacem, M.; Zeiada, W.; et al. Artificial intelligence applications in pavement infrastructure damage detection with automated three-dimensional imaging-A systematic review. Alexandria Eng. J., 2025, 117: 510−533. doi: 10.1016/j.aej.2024.11.081
2.
Tafida, A.; Alaloul, W.S.; Zawawi, N.A.B.W.; et al. Advancing smart transportation: A review of computer vision and photogrammetry in learning-based dimensional road pavement defect detection. Comput. Sci. Rev., 2025, 56: 100729. doi: 10.1016/j.cosrev.2025.100729
3.
Zhang, Y.C.; Liu, C. Real-time pavement damage detection with damage shape adaptation. IEEE Trans. Intell. Transport. Syst., 2024, 25: 18954−18963. doi: 10.1109/TITS.2024.3416508
4.
Lu, W.J.; Lan, C.Z.; Niu, C.Y.; et al. A CNN-transformer hybrid model based on CSWin transformer for UAV image object detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2023, 16: 1211−1231. doi: 10.1109/JSTARS.2023.3234161
5.
Yuan, Y.Z.; Gao, S.C.; Zhang, Z.T.; et al. Edge-cloud collaborative UAV object detection: Edge-embedded lightweight algorithm design and task offloading using fuzzy neural network. IEEE Trans. Cloud Comput., 2024, 12: 306−318. doi: 10.1109/TCC.2024. 3361858
6.
Zhu, J.Q.; Wu, Y.X.; Ma, T. Multi-object detection for daily road maintenance inspection with UAV based on improved YOLOv8. IEEE Trans. Intell. Transport. Syst. 2024, 25, 16548–16560. doi: 10.1109/TITS.2024.3437770
7.
Chen, T.Y.; Ren, J.T. Integrating GAN and texture synthesis for enhanced road damage detection. IEEE Trans. Intell. Transport. Syst., 2024, 25: 12361−12371. doi: 10.1109/TITS.2024.3373394
8.
Zeng, N.Y.; Li, X.Y.; Wu, P.S.; et al. A novel tensor decomposition-based efficient detector for low-altitude aerial objects with knowledge distillation scheme. IEEE/CAA J. Autom. Sin., 2024, 11: 487−501. doi: 10.1109/JAS.2023.124029
9.
Min, X.L.; Zhou, W.; Hu, R.; et al. LWUAVDet: A lightweight UAV object detection network on edge devices. IEEE Internet Things J., 2024, 11: 24013−24023. doi: 10.1109/JIOT.2024.3388045
10.
Wu, P.S.; Wang, Z.D.; Li, H.; et al. KD-PAR: A knowledge distillation-based pedestrian attribute recognition model with multi-label mixed feature learning network. Expert Syst. Appl., 2024, 237: 121305. doi: 10.1016/j.eswa.2023.121305
11.
Hou, Q.B.; Zhou, D.Q.; Feng, J.S. Coordinate attention for efficient mobile network design. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; IEEE: New York, 2021; pp. 13708–13717. doi:10.1109/CVPR46437.2021.01350
12.
Han, K.; Wang, Y.H.; Tian, Q.; et al. GhostNet: More features from cheap operations. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020; IEEE: New York, 2020; pp. 1577–1586. doi:10.1109/CVPR42600.2020.00165
13.
Hu, J.; Shen, L.; Sun, G. Squeeze-and-excitation networks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; IEEE: New York, 2018; pp. 7132–7141. doi:10.1109/CVPR.2018.00745
14.
Ren, S.Q.; He, K.M.; Girshick, R.; et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell., 2017, 39: 1137−1149. doi: 10.1109/TPAMI.2016.2577031
15.
He, K.M.; Gkioxari, G.; Dollár, P.; et al. Mask R-CNN. In Proceedings ofthe IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; IEEE: New York, 2017; pp. 2980–2988. doi:10.1109/ICCV.2017.322
16.
Cai, Z.W.; Vasconcelos, N. Cascade R-CNN: Delving into high quality object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; IEEE: New York, 2018; pp. 6154–6162. doi:10.1109/CVPR.2018.00644
17.
Li, C.Y.; Li, L.L.; Jiang, H.L.; et al. YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv: 2209.02976, 2022. doi:10.48550/arXiv.2209.02976
18.
Wang, A.; Chen, H.; Liu, L.; et al. YOLOv10: Real-time end-to-end object detection. In Proceedings of the 38th International Conference on Neural Information Processing Systems, Vancouver BC Canada, 10–15 December 2024; Curran Associates Inc.: Red Hook, 2024; p. 3429.
19.
Lin, T.Y.; Goyal, P.; Girshick, R.; et al. Focal loss for dense object detection. In Proceedings ofthe IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; IEEE: New York, 2017; pp. 2999–3007. doi:10.1109/ICCV.2017.324
20.
Liu, W.; Anguelov, D.; Erhan, D.; et al. SSD: Single shot MultiBox detector. In Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; Springer: Berlin/Heidelberg, Germany, 2016; pp. 21–37. doi:10.1007/978-3-319-46448-0_2
21.
Chen, H.N.; Wu, P.S.; Wen, W.M.; et al. DLA-Net: A dynamically learnable attention network for intelligent surface visual inspection of aero-engine blades. IEEE Trans. Instrum. Meas., 2025, 74: 3532114. doi: 10.1109/TIM.2025.3561440
22.
Yue, X.L.; Chen, J.D.; Zhong, G.Q. Metal surface defect detection based on metal-YOLOX. Int. J. Network Dyn. Intell., 2023, 2: 100020. doi: 10.53941/ijndi.2023.100020
23.
El-Shorbagy, M.A.; Bouaouda, A.; Nabwey, H.A.; et al. Bald eagle search algorithm: A comprehensive review with its variants and applications. Syst. Sci. Control Eng., 2024, 12: 2385310. doi: 10.1080/21642583.2024.2385310
24.
Fang, W.H.; Shen, B.; Pan, A.Q.; et al. A cooperative stochastic configuration network based on differential evolutionary sparrow search algorithm for prediction. Syst. Sci. Control Eng., 2024, 12: 2314481. doi: 10.1080/21642583.2024.2314481
25.
Li, H.; Liu, H.N.; Lan, C.B.; et al. SMWO/D: A decomposition-based switching multi-objective whale optimiser for structural optimisation of Turbine disk in aero-engines. Int. J. Syst. Sci., 2023, 54: 1713−1728. doi: 10.1080/00207721.2023.2209873
26.
Li, H.; Wang, Z.D.; Zeng, N.Y.; et al. Promoting objective knowledge transfer: A cascaded fuzzy system for solving dynamic multiobjective optimization problems. IEEE Trans. Fuzzy Syst., 2024, 32: 6199−6213. doi: 10.1109/TFUZZ.2024.3443207
27.
Sheng, M.M.; Ding, W.J.; Sheng, W.G. Differential evolution with adaptive niching and reinitialisation for nonlinear equation systems. Int. J. Syst. Sci., 2024, 55: 2172−2186. doi: 10.1080/00207721.2024.2337039
28.
Xue, J.K.; Shen, B. A survey on sparrow search algorithms and their applications. Int. J. Syst. Sci., 2024, 55: 814−832. doi: 10.1080/00207721.2023.2293687
29.
Zhang, T.H.; Liu, Q.X.; Liu, J.Y.; et al. Multiple-bipartite consensus for networked Lagrangian systems without using neighbours ’ velocity information in the directed graph. Syst. Sci. Control Eng., 2023, 11: 2210185. doi: 10.1080/21642583.2023.2210185
30.
Li, H.; Wu, P.S.; Wang, Z.D.; et al. A generalized framework of feature learning enhanced convolutional neural network for pathology-image-oriented cancer diagnosis. Comput. Biol. Med., 2022, 151: 106265. doi: 10.1016/j.compbiomed.2022.106265
31.
Liang, Y.P.; Tian, L.L.; Zhang, X.; et al. Multi-dimensional adaptive learning rate gradient descent optimization algorithm for network training in magneto-optical defect detection. Int. J. Network Dyn. Intell., 2024, 3: 100016. doi: 10.53941/IJNDI.2024.100016
32.
Yuan, Z.F.; Li, Y.; Liu, Y.; et al. Unsupervised ship detection in SAR imagery based on energy density-induced clustering. Int. J. Network Dyn. Intell., 2023, 2: 100006. doi: 10.53941/IJNDI.2023.100006
33.
Xu, J.H.; Fan, X.T.; Jian, H.D.; et al. YoloOW: A spatial scale adaptive real-time object detection neural network for open water search and rescue from UAV aerial imagery. IEEE Trans. Geosci. Remote Sens., 2024, 62: 5623115. doi: 10.1109/TGRS.2024.3395483
34.
Ye, T.; Qin, W.Y.; Zhao, Z.Y.; et al. Real-time object detection network in UAV-vision based on CNN and transformer. IEEE Trans. Instrum. Meas., 2023, 72: 2505713. doi: 10.1109/TIM.2023.3241825
35.
Zhang, Y.Z.; Wu, C.Y.; Zhang, T.; et al. Self-attention guidance and multiscale feature fusion-based UAV image object detection. IEEE Geosci. Remote Sens. Lett., 2023, 20: 6004305. doi: 10.1109/LGRS.2023.3265995
36.
Jiang, L.J.; Yuan, B.X.; Du, J.W.; et al. MFFSODNet: Multiscale feature fusion small object detection network for UAV aerial images. IEEE Trans. Instrum. Meas., 2024, 73: 5015214. doi: 10.1109/TIM.2024.3381272
37.
Lan, Z.Y.; Zhuang, F.Y.; Lin, Z.J.; et al. MFO-Net: A multiscale feature optimization network for UAV image object detection. IEEE Geosci. Remote Sens. Lett., 2024, 21: 6006605. doi: 10.1109/LGRS.2024.3382090
38.
Dai, J.F.; Qi, H.Z.; Xiong, Y.W.; et al. Deformable convolutional networks. In Proceedings ofthe IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; IEEE: New York, 2017; pp. 764–773. doi:10.1109/ICCV.2017.89
39.
Chen, J.R.; Kao, S.H.; He, H.; et al. Run, don’t walk: Chasing higher FLOPS for faster neural networks. In Proceedings ofthe 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 17–24 June 2023; IEEE: New York, 2023; pp. 12021–12031. doi:10.1109/CVPR52729.2023.01157
40.
Wang, S.X.; Jiao, H.Z.; Su, X.; et al. An ensemble learning approach with attention mechanism for detecting pavement distress and disaster-induced road damage. IEEE Trans. Intell. Transport. Syst., 2024, 25: 13667−13681. doi: 10.1109/TITS.2024.3391751
41.
Yin, T.X.; Zhang, W.; Kou, J.Q.; et al. Promoting automatic detection of road damage: A high-resolution dataset, a new approach, and a new evaluation criterion. IEEE Trans. Autom. Sci. Eng., 2025, 22: 2472−2484. doi: 10.1109/TASE.2024.3379945
42.
Li, J.; Qu, Z.; Wang, S.Y.; et al. YOLOX-RDD: A method of anchor-free road damage detection for front-view images. IEEE Trans. Intell. Transport. Syst., 2024, 25: 14725−14739. doi: 10.1109/TITS.2024.3389945
43.
Qiao, S.Y.; Chen, L.C.; Yuille, A. DetectoRS: Detecting objects with recursive feature pyramid and switchable atrous convolution. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; IEEE: New York, 2021; pp. 10208–10219. doi:10.1109/CVPR46437.2021.01008
44.
Khan, M.W.; Obaidat, M.S.; Mahmood, K.; et al. Real-time road damage detection and infrastructure evaluation leveraging unmanned aerial vehicles and tiny machine learning. IEEE Internet ThingsJ., 2024, 11: 21347−21358. doi: 10.1109/JIOT.2024.3385994
45.
Pham, S.V.H.; Van Tien Nguyen, K.; Le, L.H.; et al. Developing RTI IMS software to autonomously manage road surface quality, adapting to environmental impacts. IEEE Trans. Intell. Transport. Syst., 2024, 25: 18472−18484. doi: 10.1109/TITS.2024.3442949
46.
Yan, H.H.; Zhang, J.F. UAV-PDD2023: A benchmark dataset for pavement distress detection based on UAV images. Data Brief, 2023, 51: 109692. doi: 10.1016/j.dib.2023.109692
47.
Arya, D.; Maeda, H.; Ghosh, S.K.; et al. RDD2022: A multi-national image dataset for automatic road damage detection. Geosci. Data J., 2024, 11: 846−862. doi: 10.1002/gdj3.260

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us