MPDDNet: A Multi-Scale Parallel Network with Deformable‎Non-Local and Direction-Aware Fusion for Lane Detection in ‎Complex Environments

  • Authors

    • Shiling Huang Intelligent Manufacturing College, Nanning University, Nanning, 530200, China and Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, 86400, Malaysia
    • Nur Ariffin Mohd Zin Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, 86400, Malaysia
    • Mohd Hamdi Irwan Hamzah Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, 86400, Malaysia
    https://doi.org/10.14419/9x67sq37

    Received date: October 18, 2025

    Accepted date: November 20, 2025

    Published date: December 15, 2025

  • Lane Detection; Multi-Scale Feature Fusion; Global Context Modeling; Direction-Aware Attention; Deformable Non-Local

  • Abstract

    Lane detection in complex driving environments remains challenging due to issues such as poor visibility, occlusions, and intricate lane ‎topologies. To address these challenges, this paper proposes MPDDNet, a novel multi-scale parallel network that integrates two key com-‎ponents: a Direction-aware Adaptive Multi-scale Feature Fusion (DAM-FF) module and a Deformable Non-local (DF-NL) module. The ‎DAM-FF module explicitly embeds directional priors into multi-scale feature fusion through adaptive weighting and direction-aware spatial ‎attention, significantly enhancing detailed feature representation in challenging scenarios. The DF-NL module combines multi-scale feature ‎fusion with deformable attention mechanisms, enabling efficient global context modeling while implicitly incorporating structural priors of ‎lane geometry. Through parallel integration, these modules achieve synergistic optimization of local details and global semantics. Extensive ‎experiments on three benchmarks demonstrate that MPDDNet establishes new state-of-the-art performance, achieving 83.03% F1 score and ‎‎63.54% mF1 score on the CULane dataset. Our method also achieves remarkable results on the LLAMAS and TuSimple benchmarks, with ‎‎97.80% F1@50 and 98.40% F1 score, respectively. The consistent superiority across all three datasets and various challenging scenarios ‎validates our approach's robustness and generalization capability, providing an effective solution for lane detection in complex environments‎.

  • References

    1. X. He et al., “Monocular Lane Detection Based on Deep Learning: A Survey,” Dec. 11, 2024, arXiv: arXiv:2411.16316.
    2. J. Gamerdinger, S. Teufel, and O. Bringmann, “Datasets for Lane Detection in Autonomous Driving: A Comprehensive Review,” Apr. 11, 2025, arXiv: arXiv:2504.08540.
    3. Y. Zhang, Z. Tu, and F. Lyu, “A Review of Lane Detection Based on Deep Learning Methods,” Mech. Eng. Sci., vol. 5, no. 2, May 2024, https://doi.org/10.33142/mes.v5i2.12721.
    4. T. Zheng et al., “CLRNet: Cross Layer Refinement Network for Lane Detection,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA: IEEE, Jun. 2022, pp. 888–897. https://doi.org/10.1109/CVPR52688.2022.00097
    5. W. Hao, “Review on lane detection and related methods,” Cognitive Robotics, vol. 3, pp. 135–141, 2023, https://doi.org/10.1016/j.cogr.2023.05.004.
    6. H. Honda and Y. Uchida, “CLRerNet: Improving Confidence of Lane Detection with LaneIoU,” May 15, 2023, arXiv: arXiv:2305.08366. Ac-cessed: May 17, 2024. [Online]. Available: http://arxiv.org/abs/2305.08366.
    7. Z. Chen, Y. Liu, M. Gong, B. Du, G. Qian, and K. Smith-Miles, “Generating Dynamic Kernels via Transformers for Lane Detection,” in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France: IEEE, Oct. 2023, pp. 6812–6821. https://doi.org/10.1109/ICCV51070.2023.00629.
    8. Q. Chang and Y. Tong, “A Hybrid Global-Local Perception Network for Lane Detection,” Proc. AAAI Conf. Artif. Intell., vol. 38, no. 2, pp. 981–989, Mar. 2024, https://doi.org/10.1609/aaai.v38i2.27858.
    9. X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, "Deformable DETR: Deformable Transformers for End-to-End Object Detection," Mar. 17, 2021, arXiv: arXiv:2010.04159. Accessed: Jun. 15, 2024. [Online]. Available: http://arxiv.org/abs/2010.04159.
    10. TuSimple/tusimple-benchmark. (Oct. 04, 2025). Jupyter Notebook. TuSimple. Accessed: Oct. 18, 2025. [Online]. Available: https://github.com/TuSimple/tusimple-benchmark.
    11. Z. Cheng, G. Zhang, C. Wang, and W. Zhou, “DILane: Dynamic Instance-Aware Network for Lane Detection,” in Computer Vision – ACCV 2022, vol. 13842, L. Wang, J. Gall, T.-J. Chin, I. Sato, and R. Chellappa, Eds., in Lecture Notes in Computer Science, vol. 13842. , Cham: Springer Nature Switzerland, 2023, pp. 124–140. https://doi.org/10.1007/978-3-031-26284-5_8.
    12. Q. Qiu, H. Gao, W. Hua, G. Huang, and X. He, “PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformer,” Feb. 07, 2023, arXiv: arXiv:2209.06994. Accessed: Jul. 25, 2024. [Online]. Available: http://arxiv.org/abs/2209.06994.
    13. J.-Q. Zhang, H.-B. Duan, J.-L. Chen, A. Shamir, and M. Wang, "HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Con-volution," in *2023 IEEE/CVF International Conference on Computer Vision (ICCV)*, Paris, France: IEEE, 2023, pp. 19154-19164.
    14. C. Chen, J. Liu, C. Zhou, J. Tang, and G. Wu, “Sketch and Refine: Towards Fast and Accurate Lane Detection,” Jan. 26, 2024, arXiv: arXiv:2401.14729. Accessed: Jul. 25, 2024. [Online]. Available: http://arxiv.org/abs/2401.14729.
    15. C. Chen, J. Liu, C. Zhou, J. Tang, and G. Wu, "Sketch and Refine: Towards Fast and Accurate Lane Detection," Jan. 26, 2024, arXiv: arXiv:2401.14729. Accessed: Jul. 25, 2024. [Online]. Available: http://arxiv.org/abs/2401.14729L. Gao, Z. Qu, S. Wang, and S. Xia, “A Light-weight Neural Network Model of Feature Pyramid and Attention Mechanism for Traffic Object Detection,” IEEE Trans. Intell. Veh., vol. 9, no. 2, pp. 3422–3435, 2024, https://doi.org/10.1109/TIV.2023.3345271.
    16. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature Pyramid Networks for Object Detection," in 2017 IEEE Confer-ence on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, 2017, pp. 936-944. https://doi.org/10.1109/CVPR.2017.106.
    17. Z. Qin, P. Zhang, and X. Li, “Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification,” Jun. 15, 2022, arXiv: arXiv:2206.07389. Accessed: Jul. 31, 2024. [Online]. Available: http://arxiv.org/abs/2206.07389.
    18. L. Tabelini, R. Berriel, T. M. Paixão, C. Badue, A. F. De Souza, and T. Oliveira-Santos, "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection," in *2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, Nashville, TN, USA: IEEE, 2021, pp. 294-303. https://doi.org/10.1109/CVPR46437.2021.00036
    19. X. Pan, J. Shi, P. Luo, X. Wang, and X. Tang, "Spatial As Deep: Spatial CNN for Traffic Scene Understanding," in *Thirty-Second AAAI Confer-ence on Artificial Intelligence (AAAI-18)*, 2018. https://doi.org/10.1609/aaai.v32i1.12301
    20. J. Su, C. Chen, K. Zhang, J. Luo, and X. Wei, "Structure Guided Lane Detection," in Proceedings of the 30th ACM International Conference on Multimedia (MM '22), New York, NY, USA: ACM, 2022, pp. 1933–1941. https://doi.org/10.1145/3503161.3547915.
    21. T. Zheng et al., "RESA: Recurrent Feature-Shift Aggregator for Lane Detection," in *Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)*, 2021, pp. 3547-3555. https://doi.org/10.1609/aaai.v35i4.16469
    22. Z. Qin, H. Wang, and X. Li, "Ultra Fast Structure-aware Deep Lane Detection," in Computer Vision – ECCV 2020, vol. 12369, A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm, Eds., Cham: Springer International Publishing, 2020, pp. 276–291. https://doi.org/10.1007/978-3-030-58586-0_17
    23. L. Liu, X. Chen, S. Zhu, and P. Tan, "CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution," in *2021 IEEE/CVF International Conference on Computer Vision (ICCV)*, Montreal, QC, Canada: IEEE, 2021, pp. 3753-3762. https://doi.org/10.1109/ICCV48922.2021.00375.
    24. L. Tabelini, R. Berriel, T. M. Paixão, C. Badue, A. F. De Souza, and T. Oliveira-Santos, "PolyLaneNet: Lane Estimation via Deep Polynomial Re-gression," in 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy: IEEE, 2021, pp. 6150-6156. https://doi.org/10.1109/ICPR48806.2021.9412201.
    25. R. Liu, Z. Yuan, T. Liu, and Z. Xiong, “End-to-end Lane Shape Prediction with Transformers,” in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA: IEEE, Jan. 2021, pp. 3693–3701. https://doi.org/10.1109/WACV48630.2021.00374.
    26. A. Vaswani et al., “Attention is All You Need,” in Advances in Neural Information Processing Systems, Curran Associates, Inc., 2017. Accessed: Jun. 26, 2025. [Online]. Available: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html.
    27. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path Aggregation Network for Instance Segmentation,” Sep. 18, 2018, arXiv: arXiv:1803.01534. Accessed: Jun. 15, 2024. [Online]. Available: http://arxiv.org/abs/1803.01534.
    28. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, "Path Aggregation Network for Instance Segmentation," in *2018 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition (CVPR)*, Salt Lake City, UT: IEEE, 2018, pp. 8759-8768. https://doi.org/10.1109/CVPR.2018.00913.
    29. L. Chen et al., "PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark," in *2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, New Orleans, LA, USA: IEEE, 2022, pp. 1051-1060.
    30. B. Zhang, L. Zhang, T. Wang, Y. Wei, Z. Chen, and B. Cao, “Omni-Refinement Attention Network for Lane Detection,” Sensors, vol. 25, no. 19, p. 6150, Oct. 2025, https://doi.org/10.3390/s25196150.
    31. Q. Li et al., “PGA-Net: Polynomial Global Attention Network with Mean Curvature Loss for Lane Detection,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 1, pp. 417–429, 2024, https://doi.org/10.1109/TITS.2023.3309948.
    32. X. Wang, R. Girshick, A. Gupta, and K. He, “Non-local Neural Networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, Jun. 2018, pp. 7794–7803. https://doi.org/10.1109/CVPR.2018.00813.
    33. A. Dosovitskiy et al., "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale," in International Conference on Learning Representations (ICLR), 2021.
    34. K. Zhou and R. Zhou, “End-to-End Lane detection with One-to-Several Transformer,” May 13, 2023, arXiv: arXiv:2305.00675. Accessed: May 17, 2024. [Online]. Available: http://arxiv.org/abs/2305.00675.
    35. L. Zhuang, T. Jiang, M. Qiu, A. Wang, and Z. Huang, “Transformer Generates Conditional Convolution Kernels for End-to-End Lane Detection,” IEEE Sens. J., vol. 24, no. 17, pp. 28383–28396, Sep. 2024, https://doi.org/10.1109/JSEN.2024.3430234.
    36. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA: IEEE, Jun. 2016, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90.
    37. Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, "ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks," in *2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, Seattle, WA, USA: IEEE, 2020, pp. 11531-11539. https://doi.org/10.1109/CVPR42600.2020.01155.
    38. Z. Yang et al., “LDTR: Transformer-based Lane Detection with Anchor-chain Representation,” Mar. 21, 2024, arXiv: arXiv:2403.14354. Accessed: Jul. 25, 2024. [Online]. Available: http://arxiv.org/abs/2403.14354.
    39. K. Behrendt and R. Soussan, “Unsupervised Labeled Lane Markers Using Maps,” in 2019 IEEE/CVF International Conference on Computer Vi-sion Workshop (ICCVW), Seoul, Korea (South): IEEE, Oct. 2019, pp. 832–839. https://doi.org/10.1109/ICCVW.2019.00111.
    40. T.-Y. Lin et al., "Microsoft COCO: Common Objects in Context," in Computer Vision – ECCV 2014, vol. 8693, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds., Cham: Springer International Publishing, 2014, pp. 740–755.

  • Downloads

  • How to Cite

    Huang , S. ., Zin , N. A. M. ., & Hamzah , M. H. I. . (2025). MPDDNet: A Multi-Scale Parallel Network with Deformable‎Non-Local and Direction-Aware Fusion for Lane Detection in ‎Complex Environments. International Journal of Basic and Applied Sciences, 14(8), 263-275. https://doi.org/10.14419/9x67sq37