Road Lane Detection Using a Lightweight Architecture Based on the CBAM Attention Module

Document Type : Original Article

Authors

1 Master's student, Department of Computer Engineering, University of Sistan and Baluchestan, Zahedan, Iran

2 Assistant Professor, Department of Computer Engineering, University of Sistan and Baluchestan, Zahedan, Iran

3 Assistant Professor, Department of Information Technology, University of Sistan and Baluchestan, Zahedan, Iran

Abstract

Lane detection is a critical perception task in intelligent vehicle systems, playing a fundamental role in ensuring safe navigation for autonomous driving and advanced driver-assistance systems (ADAS). However, achieving high detection accuracy under challenging conditions—such as shadows, traffic congestion, and faded lane markings—while maintaining real-time performance remains a significant challenge. In this study, a lightweight architecture is proposed to enhance lane detection performance in complex environments through the integration of innovative strategies. The core of the proposed framework lies in the targeted incorporation of the Convolutional Block Attention Module (CBAM) into the intermediate layers of ResNet, enabling effective refinement of discriminative feature representations. Furthermore, by leveraging an advanced knowledge distillation strategy, the model achieves both high detection accuracy and real-time computational efficiency. Experimental evaluation on the CULane dataset demonstrates that the proposed method achieves an F1-score of 80.20% with a processing speed of 407 frames per second, representing improvements of 0.54% in accuracy and 1.79% in speed compared to CLRKDNet and ECBAM_ASPP, respectively. Furthermore, on the TuSimple dataset, the proposed model attains an accuracy of 96.96% while achieving the lowest false-negative rate of 1.57% among the compared methods. Compared with attention-based approaches such as ECBAM_ASPP and high-speed architectures such as UFLD, the proposed method achieves a superior balance between detection accuracy and computational efficiency, making it more suitable for real-time deployment in autonomous vehicles.

Keywords

Main Subjects

References

[1]     E.‌‌Szumska, «Electric vehicle charging infrastructure along highways in the EU», Energies, vol. 16,no. 2, pp. 895, Jan. 2023.
[2]     World Health Organization, Compendium of WHO and Other UN Guidance in Health and Environment, 2024 Update. Geneva, Switzerland: World Health Organization, Jul. 2024.
[3]      X. Ma, W. Ouyang, A. Simonelli, and E. Ricci, “3D object detection from images for autonomous driving: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 5, pp. 3537–3556, 2023.
[4]     A. Eskandarian, ed, Handbook of Intelligent Vehicles, vol. 2, pp. 165–232. London, U.K.: Springer, 2012.
[5]     A. Gurghian, T. Koduri, S. V. Bailur, K. J. Carey, and V. N. Murali, “DeepLanes: End-to-end lane position estimation using deep neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 38–45, 2016.
[6]     B. He, R. Ai, Y. Yan, and X. Lang, “Accurate and robust lane detection based on dual-view convolutional neutral network,” in 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 1041–1046, Jun. 2016
[7]     D. Liang, Y. C. Guo, S. K. Zhang, T. J. Mu, and X. Huang, “Lane detection: A survey with new results,” J. Comput. Sci. Technol, vol. 35, no. 3, pp. 493-505, May 2020. 
[8]     C. Liu, X. Li, Q. Liu, F. Yang, Z. Li, and M. Li, “A review of vision-based road detection technology for unmanned vehicles,” in 2023 IEEE Intelligent Vehicles Symposium (IV), pp. 1-8, Jun. 2023.
[9]     F. Ma, X. Yan, G. Zhao, X. Xu, Y. Liu, J. Ma, and M. Liu, “Every dataset counts: Scaling up monocular 3D object detection with joint datasets training,” in 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 11574-11580, Oct. 2024
[10] F. Ma, S. Wang, and M. Liu, “An automatic multi-lidar extrinsic calibration algorithm using corner planes,” in 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 235-240, Dec. 2022.
[11] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional block attention module,” in Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19, 2018.
[12] X. Pan, “CULane: A large-scale dataset for lane detection,” GitHub Pages. Available: https://xingangpan.github.io/projects/CULane.html
[13] TuSimple, “TuSimple benchmark,” GitHub, 2017. Available: https://github. com/TuSimple/tusimple- benchmark 
[14] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.
[15] G. Hinton, O.Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv:1503.02531, Mar. 2015
[16] W. Qi, G. Zhao, F. Ma, L. Zheng, J. Ma, and M. Liu, “CLRKDNet: Speeding up lane detection with knowledge  distillation,” in 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), pp. 679–686, Sep. 2024.
[17] X. Gu, Q. Huang, and C. Du, "Lane Detection Based on ECBAM_ASPP Model," Sensors, vol. 24, no. 24, p. 8098, Dec. 2024
[18] L. Tabelini, R. Berriel, T. M. Paixao, C. Badue, A. F. De Souza, and T. Oliveira-Santos, "Keep your eyes on the lane: Real-time attention-guided lane detection," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, , pp. 294-302, 2021
[19] G. Zhao, F. Ma, W. Qi, Y. Liu, M. Liu, and J. Ma, "CurbNet: Curb detection framework based on LiDAR point cloud segmentation," IEEE Trans. Intell. Transp. Syst, pp. , Feb. 2025
[20] C. Chen, L. Liu, S. Wan, X. Hui, and Q. Pei, "Data dissemination for industry 4.0 applications in internet of vehicles based on short-term traffic prediction," ACM Trans. Internet Technol, vol. 22, no. 1, pp. 1-8, Oct. 2021
[21] X. Pan, J. Shi, P. Luo, X. Wang, and X. Tang, "Spatial as deep: Spatial cnn for trafficscene understanding," in Proc. AAAI Conf. Artif. Intell, vol. 32, no. 1, pp. , 2018.
[22] T. Zheng et al., "Resa: Recurrent feature-shift aggregator for lane detection," in Proc. AAAI Conf. Artif. Intell, vol. 35, no. 4, pp. 3547-3554, 2021
[23] Z. Qin, H. Wang, and X. Li, "Ultra fast structure-aware deep lane detection," in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16 , pp. 276-291, Aug. 2020.
[24] X. Li, J. Li, X. Hu, and J. Yang, "Line-cnn: End-to-end traffic line detection with line proposal unit," IEEE Trans. Intell. Transp. Syst, vol. 21, no. 1, pp. 248-258, Jan. 2019
[25] D. Jin, W. Park, S.-G. Jeong, H. Kwon, and C.-S. Kim, "Eigenlanes: Data-driven lane descriptors for structurally diverse lanes," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit, pp. 17163-17171, 2022
[26] L. Liu, X. Chen, S. Zhu, and P. Tan, "Condlanenet: a top-to-down lane detection framework based on conditional convolution," Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3773-3782, 2021.
[27] S. Yoo et al., “End-to-end lane marker detection via row-wise classification,” Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops, pp. 1006–1007, Jun. 2020.
[28] T. Zheng et al., "CLRNet: Cross layer refinement network for lane detection," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit, pp. 898-907, 2022
[29] Z. Ge, "Yolox: Exceeding yolo series in 2021," arXiv preprint arXiv:2107.08430, 2021.
[30] Z. Qin, P. Zhang, and X. Li, "Ultra fast deep lane detection with hybrid anchor driven ordinal classification," IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 5, pp. 2555-2568, Jun. 2022.
[31] J. Han, X. Deng, X. Cai, Z. Yang, H. Xu, C. Xu, and X. Liang, "Laneformer: Object-aware row-column transformers for lane detection," in Proc. AAAI Conf. Artif. Intell.,vol. 36, no. 1, pp. 799-807, Jun. 2022.
[32] Z. Qu, H. Jin, Y. Zhou, Z. Yang, and W. Zhang, "Focus on local: Detecting lane marker from bottom up via key point," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 14122-14130, 2021 
[33] J. Wang et al, "A keypoint-based global association network for lane detection," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 1392-1401, 2022 
[34] R. Liu, Z. Yuan, T. Liu, and Z. Xiong, "End-to-end lane shape prediction with transformers," in Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis., pp. 3694-3702, 2021
[35] Y. Hou, Z. Ma, C. Liu, and C. C. Loy, "Learning lightweight lane detection CNNs by self attention  distillation," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), pp. 1013-1021, 2019.
Applied and basic Machine intelligence research
Volume 4, Issue 1
May 2026
Pages 147-165

Files

Share

How to cite

Statistics