PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Lane detection is an essential task for autonomous vehicles. Deep learning-based lane detection methods are leading development in this sector. This paper proposes an algorithm named Deep Learning-based Lane Detection (DLbLD), a Convolutional Neural Network (CNN)-based lane detection algorithm. The presented paradigm deploys CNN to detect line features in the image block, predict a point on the lane line part, and project all the detected points for each frame into one-dimensional form before applying K-mean clustering to assign points to related lane lines. Extensive tests on different benchmarks were done to evaluate the performance of the proposed algorithm. The results demonstrate that the introduced DLbLD scheme achieves state-of-the-art performance, where F1 scores of 97.19 and 79.02 have been recorded for TuSimple and CU-Lane benchmarks, respectively. Nevertheless, results indicate the high accuracy of the proposed algorithm.

• Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., … & Zheng, X. (2016, November 2-4). TensorFlow: A system for large-scale machine learning. [Paper presentation]. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), Savannah, USA.

• Abualsaud, H., Liu, S., Lu, D., Situ, K., Rangesh, A., & Trivedi, M. M. (2021). LaneAF: Robust multi-lane detection with affinity fields. IEEE Robotics and Automation Letters, 6(4), 7477–7484. https://doi.org/10.1109/lra.2021.3098066

• Al-Jarrah, R., Al-Jarrah, M., & Roth, H. (2018). A novel edge detection algorithm for mobile robot path planning. Journal of Robotics, 2018, Article 1969834. https://doi.org/10.1155/2018/1969834

• Aly, M. (2008, June 4-6). Real time detection of lane markers in urban streets. [Paper presentation]. IEEE Intelligent Vehicles Symposium, Eindhoven, Netherlands. https://doi.org/10.1109/IVS.2008.4621152

• Chen, Y., & Xiang, Z. (2022). Lane mark detection with pre-aligned spatial-temporal attention. Sensors, 22(3), Article 794. https://doi.org/10.3390/s22030794

• Chollet, F. (n.d.). Keras [Pyhton]. Github.com. https://github.com/keras-team/keras

• He, K., Zhang, X., Ren, S., & Sun, J. (2016, June 27-30). Deep residual learning for image recognition. [Paper presentation]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA. https://doi.org/10.1109/cvpr.2016.90

• Hou, Y., Ma, Z., Liu, C., & Loy, C. C. (2019, October 27-November 2). Learning lightweight lane detection CNNs by self attention distillation. [Paper presentation]. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea. https://doi.org/10.1109/iccv.2019.00110

• Jiang, R., Klette, R., Vaudrey, T., & Wang, S. (2009, September 2-4). New lane model and distance transform for lane detection and tracking. [Paper presentation]. Computer Analysis of Images and Patterns: 13th International Conference (CAIP), Munster, Germany. https://doi.org/10.1007/978-3-642-03767-2_127

• Kim, Z. (2008). Robust lane detection and tracking in challenging scenarios. IEEE Transactions on Intelligent Transportation Systems, 9(1), 16–26. https://doi.org/10.1109/TITS.2007.908582

• Ko, Y., Lee, Y., Azam, S., Munir, F., Jeon, M., & Pedrycz, W. (2022). Key points estimation and point instance segmentation approach for lane detection. IEEE Transactions on Intelligent Transportation Systems, 23(7), 8949–8958. https://doi.org/10.1109/tits.2021.3088488

• Lee, D. G., & Kim, Y. K. (2022). Joint semantic understanding with a multilevel branch for driving perception. Applied Sciences, 12(6), Article 2877. https://doi.org/10.3390/app12062877

• Lee, M., Lee, J., Lee, D., Kim, W., Hwang, S., & Lee, S. (2022, January 3-8). Robust lane detection via expanded self attention. [Paper presentation]. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, USA.

• Liu, G., Worgotter, F., & Markelic, I. (2010, June 21-24). Combining statistical Hough transform and particle filter for robust lane detection and tracking. [Paper presentation]. IEEE Intelligent Vehicles Symposium, La Jolla, USA. https://doi.org/10.1109/IVS.2010.5548021

• Liu, L., Chen, X., Zhu, S., & Tan, P. (2021, October 10-17). CondLaneNet: A top-to-down lane detection framework based on conditional convolution. [Paper presentation]. IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada. https://doi.org/10.1109/iccv48922.2021.00375

• Liu, R., Yuan, Z., Liu, T., & Xiong, Z. (2021, January 3-8). End-to-end lane shape prediction with transformers. [Paper presentation]. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, USA. https://doi.org/10.1109/WACV48630.2021.00374

• Lloyd, S. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129–137. https://doi.org/10.1109/TIT.1982.1056489

• Loshchilov, I., & Hutter, F. (2017). SGDR: Stochastic gradient descent with warm restarts. arXiv. https://doi.org/10.48550/arXiv.1608.03983.

• Neven, D., De Brabandere, B., Georgoulis, S., Proesmans, M., & Van Gool, L. (2018, June 26-30). Towards end-to-end lane detection: An instance segmentation approach. [Paper presentation]. IEEE Intelligent Vehicles Symposium (IV), Changshu, China. https://doi.org/10.1109/ivs.2018.8500547

• Pan, X., Shi, J., Luo, P., Wang, X., & Tang, X. (2018). Spatial as deep: Spatial CNN for Traffic scene understanding. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), Article 7277. https://doi.org/10.1609/aaai.v32i1.12301

• Philion, J. (2019, June 15-20). Fastdraw: Addressing the long tail of lane detection by adapting a sequential prediction network. [Paper presentation]. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California. https://doi.org/10.1109/cvpr.2019.01185

• Pizzati, F., Allodi, M., Barrera, A., & García, F. (2020). Lane detection and classification using cascaded CNNs. In R. Moreno-Diaz, F. Pichler & A. Quesada-Arencibia (Eds.) Computer aided systems theory–EUROCAST 2019 (pp. 95–103). Springer. https://doi.org/10.1007/978-3-030-45096-0_12

• Qin, Z., Wang, H., & Li, X. (2020). Ultra fast structure-aware deep lane detection. In A. Vedaldi, H. Bischof, T. Borx & J. Frahm (Eds.) Computer vision–ECCV 2020 (pp. 276–291). Springer. https://doi.org/10.1007/978-3-030-58586-0_17

• Rossum, G. V., & Drake, F. L. (1995). Python reference manual. Centrum voor Wiskunde en Informatica.

• Shengli, F., Yuzhi, Z., & Xiaohui, B. (2023). Lane marker detection based on multihead self-attention. Mobile Information Systems, 2023, Article 2075022. https://doi.org/10.1155/2023/2075022

• Tabelini, L., Berriel, R., Paixão, T. M., Badue, C., De Souza, A. F., & Oliveira-Santos, T. (2021a, June 20-25). Keep your eyes on the lane: Real-time attention-guided lane detection. [Paper presentation]. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, Tennessee. https://doi.org/10.1109/cvpr46437.2021.00036

• Tabelini, L., Berriel, R., Paixão, T. M., Badue, C., De Souza, A. F., & Oliveira-Santos, T. (2021b, January 10-15). Polylanenet: Lane estimation via deep polynomial regression. [Paper presentation]. 25th International Conference on Pattern Recognition (ICPR), Milan, Italy. https://doi.org/10.1109/icpr48806.2021.9412265

• Tang, J., Li, S., & Liu, P. (2021). A review of lane detection methods based on deep learning. Pattern Recognition, 111, Article 107623. https://doi.org/10.1016/j.patcog.2020.107623

• Xie, T., Yin, M., Zhu, X., Sun, J., Meng, C., & Bei, S. (2023). A fast and robust lane detection via online re-parameterization and hybrid attention. Sensors, 23(19), Article 8285. https://doi.org/10.3390/s23198285

• Xin, L., Yingping, H., & Zhenming, L. (2023). Axial attention-guided anchor classification lane detection. Opto-Electronic Engineering, 50(7), Article 230079-1. https://doi.org/10.12086/oee.2023.230079

• Xu, H., Wang, S., Cai, X., Zhang, W., Liang, X., & Li, Z. (2022). Curvelane-NAS: Unifying lane-sensitive architecture search and adaptive point blending. In A. Vedaldi, H. Bischof, T. Brox & J. Frahm (Eds.) Computer vision–ECCV 2020 (pp. 689–704). Springer. https://doi.org/10.1007/978-3-030-58555-6_41

• Yang, Q., Ma, Y., Li, L., Su, C., Gao, Y., Tao, J., Huang, Z., & Jiang, R. (2023). Lightweight lane line detection based on learnable cluster segmentation with self-attention mechanism. IET Intelligent Transport Systems, 17(3), 522–533. https://doi.org/10.1049/itr2.12277

• Yanga, J., Zhang, L., & Lu, H. (2023). Lane detection with versatile atrousformer and local semantic guidance. Pattern Recognition, 113, Article 109053. https://doi.org/10.1016/j.patcog.2022.109053

• Yao, X., Wang, Y., Wu, Y., He, G., & Luo, S. (2023). MLP-Based efficient convolutional neural network for lane detection. IEEE Transactions on Vehicular Technology, 72(10), 12602-122614. https://doi.org/10.1109/TVT.2023.3275571

• Yao, Z., & Chen, X. (2022). Efficient lane detection technique based on lightweight attention deep neural network. Journal of Advanced Transportation, 2022, Article 5134437. https://doi.org/10.1155/2022/5134437

• Yoo, S., Lee, H., Myeong, H., Yun, S., Park, H., Cho, J., & Kim, D. H. (2020, June 14-19). End-to-end lane marker detection via row-wise classification. [Paper presentation]. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, USA. https://doi.org/10.1109/cvprw50498.2020.00511

• Zang, J., Zhou, W., Zhang, G., & Duan, Z. (2018, November 12-15). Traffic lane detection using fully convolutional neural network. [Paper presentation]. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, Hawaii. https://doi.org/10.23919/APSIPA.2018.8659684