面向铁路道岔情景下的列车轨道区域检测方法

doi:10.3969/j.issn.0255-8297.2024.01.012

摘要/Abstract

摘要： 列车前方铁路轨道区域的检测是列车主动防撞技术的关键环节，现有的铁路区域分割方法多用于简单情景下的轨道检测，难以应对实际运行中的铁路道岔等复杂场景。该文提出了一种面向铁路道岔情景下的列车轨道区域检测方法，解决了现有技术在铁路道岔下难以检测列车实际运行区域的问题。首先，设计了一种基于信息融合的铁路轨道区域分割模型，针对铁路左右钢轨之间难以匹配的问题，对铁路区域和钢轨进行分割并利用其分割结果进行钢轨匹配。其次，设计了一种基于反向透视变换的铁路区域重建方法，通过保留钢轨的关键点来重建铁路区域，同时使用基于分组卷积的铁路道岔分类模型对道岔方向进行识别。实验结果表明，提出的方法在复杂环境下可达到较高的精度，像素准确率可达98.67%，平均交并比可达98.12%，具有在列车上应用的潜力。

关键词: 轨道区域检测, 列车自动驾驶, 铁路区域重建, 道岔识别

Abstract: The detection of the railway track area in front of the train is a key link in active train collision avoidance technology. The existing railway area segmentation methods are mostly used for track detection in simple scenarios, posing challenges when confronted with complex scenarios such as railway switches in actual operation. We propose a method for detecting railway track areas for railway switches, which solves the problem that existing technology encounters difficulty in detecting the actual running area of trains under railway switches. First, a railway track area segmentation model based on information fusion is proposed. Aiming at the problem of difficulty in matching the left and right rails of the railway, the railway area and the rails are segmented and the segmentation results are used for rail matching. Second, a railway area reconstruction method based on inverse perspective transformation is designed to reconstruct the railway area by preserving the key points of the rails. Meanwhile, a railway switch classification model based on grouped convolution is used to identify the switch direction. Experimental results show that the proposed method achieves high accuracy in complex environments, with pixel accuracy (PA) index of 98.67% and Mean Intersection over Union (MioU) index of 98.12%, showcasing its potential applicability to trains.

Key words: track area detection, train automatic driving, railway area reconstruction, switch identification

中图分类号:

TP399

陈裔鋆, 陈羽, 滕飞. 面向铁路道岔情景下的列车轨道区域检测方法[J]. 应用科学学报, 2024, 42(1): 145-160.

CHEN Yijun, CHEN Yu, TENG Fei. Track Area Detection for Railway Switches[J]. Journal of Applied Sciences, 2024, 42(1): 145-160.

参考文献

[1] 王猛, 刘佳星, 侯雪情, 等. 高铁沿线突发事件形成机制[J]. 中国安全科学学报, 2020, 30(增刊1): 179-187. Wang M, Liu J X, Hou X Q, et al. Formation mechanism of emergencies along high-speed rail [J]. China Safety Science Journal, 2020, 30(Suppl.1): 179-187. (in Chinese)
[2] Ren K Y, Hou H C, Li S Y, et al. LaneDraw: cascaded lane and its bifurcation detection with nested fusion [J]. Science China Technological Sciences, 2021, 64(6): 1238-1249.
[3] Ghanem S, Kanungo P, Panda G, et al. An improved and low-complexity neural network model for curved lane detection of autonomous driving system [J]. Soft Computing, 2023, 27(1): 493-504.
[4] Lu P P, Xu S B, Peng H E. Graph-embedded lane detection [J]. IEEE Transactions on Image Processing, 2021, 30: 2977-2988.
[5] Maire F, Bigdeli A. Obstacle-free range determination for rail track maintenance vehicles [C]//International Conference on Control Automation Robotics & Vision, 2011: 2172-2178.
[6] Espino J C, Stanciulescu B, Forin P. Rail and turnout detection using gradient information and template matching [C]//IEEE International Conference on Intelligent Rail Transportation Proceedings, 2013: 233-238.
[7] Espino J C, Stanciulescu B. Rail extraction technique using gradient information and a priori shape model [C]//IEEE Conference on Intelligent Transportation Systems, 2012: 1132-1136.
[8] Nassu B T, Ukai M. Rail extraction for driver support in railways [C]//IEEE Intelligent Vehicles Symposium (IV), 2011: 83-88.
[9] 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.
[10] Zwemer M H, Van De Wouw D W J M, Jaspers E G T, et al. A vision-based approach for tramway rail extraction [C]//Video Surveillance and Transportation Imaging Applications, 2015, 9407: 227-239.
[11] Wang Z Y, Wu X K, Yu G Z, et al. Efficient rail area detection using convolutional neural network [J]. IEEE Access, 2018, 6: 77656-77664.
[12] Wang Y,Wang L D, Hu Y H, et al. RailNet: a segmentation network for railroad detection [J]. IEEE Access, 2019, 7: 143772-143779.
[13] Li X X, Zhu L Q, Yu Z J, et al. Vanishing point detection and rail segmentation based on deep multi-task learning [J]. IEEE Access, 2020, 8: 163015-163025.
[14] Romera E, Alvarez J M, Bergasa L M, et al. ERFNet: efficient residual factorized Conv- Net for real-time semantic segmentation [J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 19(1): 263-272.
[15] Tastimur C, Karakose M, Akin E. A vision based condition monitoring approach for rail switch and level crossing using hierarchical SVM in railways [J]. International Journal of Applied Mathematics Electronics and Computers, 2016: 319-325.
[16] Zhang S J, Tang T, Liu J T. A hazard analysis approach for the SOTIF in intelligent railway driving assistance systems using STPA and complex network [J]. Applied Sciences, 2021, 11(16): 7714.
[17] Zhu X Z, Su W J, Lu L W, et al. Deformable DETR: deformable transformers for end-to-end object detection [DB/OL]. 2020[2023-06-29]. https://arxiv.org/abs/2010.04159.
[18] Wang Q L, Wu B G, Zhu P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]//IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2020: 11534-11542.
[19] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [DB/OL]. 2017[2023-06-29]. https://arxiv.org/abs/1706.03762.
[20] Guo Z C, Hall R W. Parallel thinning with two-subiteration algorithms [J]. Communications of the ACM, 1989, 32(3): 359-373.
[21] Zhou T Y, Zhao Y, Wu J. ResNeXt and Res2Net structures for speaker verification [C]//IEEE Spoken Language Technology Workshop (SLT), 2021: 301-307.
[22] Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module [C]//European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 3-19.
[23] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
[24] Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[25] He K M, Gkioxari G, Dollár P, et al. Mask R-CNN [C]//IEEE International Conference on Computer Vision, 2017: 2961-2969.
[26] Chen L C, Zhu Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation [C]//European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 801-818.
[27] Yang S Y, Yu G Z, Wang Z Y, et al. A topology guided method for rail-track detection [J]. IEEE Transactions on Vehicular Technology, 2021, 71(2): 1426-1438.
[28] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [DB/OL]. 2014[2023-06-29]. https://arxiv.org/abs/1409.1556.
[29] Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2818-2826.
[30] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.