Rail Line Detection Algorithm Based on Improved CLRNet

doi:10.1007/s12204-023-2683-y

Abstract

Abstract: In smart driving for rail transit, a reliable obstacle detection system is an important guarantee for the safety of trains. Therein, the detection of the rail area directly affects the accuracy of the system to identify dangerous targets. Both the rail line and the lane are presented as thin line shapes in the image, but the rail scene is more complex, and the color of the rail line is more difficult to distinguish from the background. By comparison, there are already many deep learning-based lane detection algorithms, but there is a lack of public datasets and targeted deep learning detection algorithms for rail line detection. To address this, this paper constructs a rail image dataset RailwayLine and labels the rail line for the training and testing of models. This dataset contains rich rail images including single-rail, multi-rail, straight rail, curved rail, crossing rails, occlusion, blur, and different lighting conditions. To address the problem of the lack of deep learning-based rail line detection algorithms, we improve the CLRNet algorithm which has an excellent performance in lane detection, and propose the CLRNet-R algorithm for rail line detection. To address the problem of the rail line being thin and occupying fewer pixels in the image, making it difficult to distinguish from complex backgrounds, we introduce an attention mechanism to enhance global feature extraction ability and add a semantic segmentation head to enhance the features of the rail region by the binary probability of rail lines. To address the poor curve recognition performance and unsmooth output lines in the original CLRNet algorithm, we improve the weight allocation for line intersection-over-union calculation in the original framework and propose two loss functions based on local slopes to optimize the model’s local sampling point training constraints, improving the model’s fitting performance on curved rails and obtaining smooth and stable rail line detection results. Through experiments, this paper demonstrates that compared with other mainstream lane detection algorithms, the algorithm proposed in this paper has a better performance for rail line detection.

Key words: rail line detection, attention mechanism, semantic segmentation, loss function, CLRNet algorithm

摘要： 在轨道交通智慧驾驶中，可靠的障碍物检测系统是列车安全的重要保障，其中对铁轨区域的检测直接影响系统辨别危险目标的准确性。铁轨线与车道线在图像中都呈现为细长线条状，但是轨道场景的环境更复杂，铁轨线的颜色更难以与背景区分。相较而言，目前已经有许多基于深度学习的车道线检测算法，铁轨线检测却缺乏公开的数据集以及针对性的深度学习检测算法。为此本文构建了一个铁轨图像数据集RailwayLine并对铁轨线进行标注用于检测模型的训练和测试。该数据集包含单轨道、多轨道、直轨、弯轨、交叉、遮挡、模糊和不同光照条件等丰富的铁轨图像；针对目前缺少基于深度学习的铁轨线检测算法的问题，我们改进了在车道线方面性能优异的CLRNet算法，提出了铁轨线检测算法CLRNet-R；针对铁轨线在成像中线条细长，所占像素少，难以从复杂背景中区分的问题，我们引入注意力机制，提升全局特征提取能力，并增加语义分割头，利用铁轨二值概率增强铁轨线区域的特征；针对原CLRNet算法识别弯轨性能差、输出线条不光滑的问题，我们改进了原框架中线条交并比计算的权重分配，并提出两种基于局部斜率的损失，优化模型局部采样点的训练约束，提升模型对弯轨的拟合性能，获取光滑、稳定的铁轨线检测结果。本文通过实验证明，与其他主流的车道线检测算法相比，所提出的算法在铁轨线检测任务中具有更好的性能。

关键词: 铁轨线检测，注意力，语义分割头，损失函数，CLRNet算法

CLC Number:

U216 TP391

ZHOU Bowei, XING Guanyu, LIU Yanli. Rail Line Detection Algorithm Based on Improved CLRNet[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 923-934.

References

[1] LIESENKOTTER B H C. Obstruction detection for people movers operating on conventional small branch railways[C]//IEEE International Conference on Intelligent Vehicles. Stuttgart: IEEE, 1998: 280-284.

[2] WOHLFEIL J. Vision based rail track and switch recognition for self-localization of trains in a rail network [C]//2011 IEEE Intelligent Vehicles Symposium. Baden-Baden: IEEE, 2011: 1025-1030.

[3] NIU H X, HOU T. Fast detection study of foreign object intrusion on railway track [J]. Archives of Transport, 2018, 47(3): 79-89.

[4] BALLARD D H. Generalizing the Hough transform to detect arbitrary shapes [J]. Pattern Recognition, 1981, 13(2): 111-122.

[5] KALMAN R E. A new approach to linear filtering and prediction problems [J]. Journal of Basic Engineering, 1960, 82(1): 35-45.

[6] ZHANG Y Z, GUO W. Intelligent detection and early warning system of railway track[M]// Artificial intelligence and security. Cham: Springer, 2021: 505-515.

[7] NEVEN D, DE BRABANDERE B, GEORGOULIS S, et al. Towards end-to-end lane detection: An instance segmentation approach [C]//2018 IEEE Intelligent Vehicles Symposium. Changshu: IEEE, 2018: 286-291.

[8] ZHENG T, FANG H, ZHANG Y, et al. RESA: Recurrent feature-shift aggregator for lane detection [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(4): 3547-3554.

[9] TABELINI L, BERRIEL R, PAIXÃO T M, et al. PolyLaneNet: lane estimation via deep polynomial regression [C]//2020 25th International Conference on Pattern Recognition. Milan: IEEE, 2021: 6150-6156.

[10] QU Z, JIN H, ZHOU Y, et al. Focus on local: Detecting lane marker from bottom up via key point [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 14117-14125.

[11] ZHENG T, HUANG Y F, LIU Y, et al. CLRNet: cross layer refinement network for lane detection [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 888-897.

[12] TABELINI L, BERRIEL R, PAIXÃO T M, et al. Keep your eyes on the lane: Real-time attention-guided lane detection [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 294-302.

[13] QI Z Q, TIAN Y J, SHI Y. Efficient railway tracks detection and turnouts recognition method using HOG features [J]. Neural Computing and Applications, 2013, 23(1): 245-254.

[14] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 886-893.

[15] NASSU B T, UKAI M. Rail extraction for driver support in railways [C]//2011 IEEE Intelligent Vehicles Symposium. Baden-Baden: IEEE, 2011: 83-88.

[16] CANNY J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698.

[17] KALELI F, AKGUL Y S. Vision-based railroad track extraction using dynamic programming [C]//2009 12th International IEEE Conference on Intelligent Transportation Systems. St. Louis: IEEE, 2009: 1-6.

[18] HE D Q, ZOU Z H, CHEN Y J, et al. Rail transit obstacle detection based on improved CNN [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-14.

[19] RAMPRIYA R S, SUGANYA R, SABARINATHAN, et al. Object detection in railway track using deep learning techniques[M]// Topical drifts in intelligent computing. Singapore: Springer, 2022: 107-115.

[20] YU M Y, YANG P, WEI S. Railway obstacle detection algorithm using neural network [C]// 6th International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation (CDMMS 2018). Busan: AIP, 2018: 040017.

[21] YE T, WANG B C, SONG P, et al. Automatic railway traffic object detection system using feature fusion refine neural network under shunting mode [J]. Sensors, 2018, 18(6): 1916.

[22] YE T, ZHANG X, ZHANG Y, et al. Railway traffic object detection using differential feature fusion convolution neural network [J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1375-1387.

[23] LI J, ZHOU F Q, YE T. Real-world railway traffic detection based on faster better network [J]. IEEE Access, 2018, 6: 68730-68739.

[24] WANG Y, TEOH E K, SHEN D G. Lane detection and tracking using B-Snake [J]. Image and Vision Computing, 2004, 22(4): 269-280.

[25] MCCALL J C, TRIVEDI M M. Video-based lane estimation and tracking for driver assistance: Survey, system, and evaluation [J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 20-37.

[26] MA C, XIE M. A method for lane detection based on color clustering [C]//2010 Third International Conference on Knowledge Discovery and Data Mining. Phuket: IEEE, 2010: 200-203.

[27] CÁCERES HERNÁNDEZ D, KURNIANGGORO L, FILONENKO A, et al. Real-time lane region detection using a combination of geometrical and image features [J]. Sensors, 2016, 16(11): 1935.

[28] LI Y D, CHEN L G, HUANG H B, et al. Nighttime lane markings recognition based on Canny detection and Hough transform [C]//2016 IEEE International Conference on Real-time Computing and Robotics. Angkor Wat: IEEE, 2016: 411-415.

[29] OTSU N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.

[30] DING Y, XU Z, ZHANG Y B, et al. Fast lane detection based on bird’s eye view and improved random sample consensus algorithm [J]. Multimedia Tools and Applications, 2017, 76(21): 22979-22998.

[31] FISCHLER M A, BOLLES R C. Random sample consensus [J]. Communications of the ACM, 1981, 24(6): 381-395.

[32] LEE M, JANG C, SUNWOO M. Probabilistic lane detection and lane tracking for autonomous vehicles using a cascade particle filter [J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2015, 229(12): 1656-1671.

[33] WANG J T, HONG W, GONG L. Lane detection algorithm based on density clustering and RANSAC [C]//2018 Chinese Control and Decision Conference. Shenyang: IEEE, 2018: 919-924.

[34] ESTER M, KRIEGEL H P, SANDER J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]// 2nd International Conference on Knowledge Discovery and Data Mining. Menlo Park: AAAI Press, 1996: 226-231.

[35] PAN X G, SHI J P, LUO P, et al. Spatial as deep: Spatial CNN for traffic scene understanding [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 7276-7283.

[36] ZOU Q, JIANG H W, DAI Q Y, et al. Robust lane detection from continuous driving scenes using deep neural networks [J]. IEEE Transactions on Vehicular Technology, 2020, 69(1): 41-54.

[37] GHAFOORIAN M, NUGTEREN C, BAKA N, et al. EL-GAN: Embedding loss driven generative adversarial networks for lane detection[M]// Computer vision – ECCV 2018 Workshops. Cham: Springer, 2019: 256-272.

[38] LI X, LI J, HU X L, et al. Line-CNN: End-to-end traffic line detection with line proposal unit [J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(1): 248-258.

[39] FENG Z Y, GUO S H, TAN X, et al. Rethinking efficient lane detection via curve modeling [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 17041-17049.

[40] WANG J S, MA Y C, HUANG S F, et al. A keypoint-based global association network for lane detection [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 1382-1391.

[41] LIU L Z, CHEN X H, ZHU S Y, et al. CondLaneNet: a top-to-down lane detection framework based on conditional convolution [C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 3753-3762.

[42] LIU K, YANG K F, ZHANG J H, et al. S2SNet: A pretrained neural network for superconductivity discovery [M]//Proceedings of the thirty-first international joint conference on artificial intelligence. San Francisco: Margan Kaufmann, 2022: 5101-5107.

[43] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.