基于图像处理的轨旁组合信号灯识别方法

doi:10.16180/j.cnki.issn1007-7820.2023.07.002

摘要/Abstract

摘要：

对列车轨旁信号灯进行准确辨识是保障列车安全运行的重要措施。然而,对于轨道系统而言,除了通常的单色信号灯外,还有组合(两种颜色)信号灯的指示方式。针对轨旁组合信号灯的识别问题,文中提出了一种基于图像处理技术对位于列车前方150 m内的轨旁组合信号灯的识别方法。根据组合信号灯的颜色和形状特征,采用颜色分割、形态学处理、霍夫变换等手段提取组合信号灯的候选区域。同时利用组合信号灯位于当前轨道右侧的位置特征以及组合信号灯之间圆心距的距离特征,定位其位置并识别组合灯颜色。实验结果表明,该方法能准确定位和识别轨旁组合信号灯,对绿与黄、两绿和两黄这3种组合灯的识别率分别为94.14%、96.21%、86.67%。

关键词: 轨旁组合信号灯, 图像处理, 颜色分割, 形态学操作, 霍夫变换, 边缘检测, 轨道提取, 图像识别

Abstract:

The trackside signal light is an important guidance for a running train in a rail transportation system. However, the combined trackside signal light included two colors is also used as a specific sign in addition to the usual single color signal light. In order to solve the recognition problem of the combined trackside signal light, a method based on image processing technology is employed to recognize the combined trackside signal light located within 150 m in front of train. As a result, the candidate region characteristics of the combined trackside signal light are extracted by color segmentation, morphological processing, and Hough transform. On the other hand, the combined trackside signal light can be positioned on the right of running rail train. The central spacing between two single lights can determine whether or not existing combined trackside signal light to remove the possible interferences from other lights or environment. The experimental results indicate that this method can accurately locate and recognize the combined trackside signal light, and the color correction ratio is 94.14% for green and yellow light, 96.21% for two green lights, 86.67% for two yellow lights.

Key words: combined trackside signal light, image processing, color segmentation, morphological operation, Hough transform, edge detection, track extraction, image recognition

中图分类号:

TN99

郭齐成,沈拓,张轩雄. 基于图像处理的轨旁组合信号灯识别方法[J]. 电子科技, 2023, 36(7): 8-15.

GUO Qicheng,SHEN Tuo,ZHANG Xuanxiong. Recognition Method of the Combined Trackside Signal Light Based on Image Processing[J]. Electronic Science and Technology, 2023, 36(7): 8-15.

图/表 11

图1

表1

表2

图2

图3

图4

图5

图6

图7

图8

表3

参考文献 21

[1]	刘伯鸿, 李国宁. 城市轨道交通信号[M]. 成都: 西南交通大学出版社, 2011:25-68.
	Liu Bohong, Li Guoning. Urban rail transit signal[M]. Chengdu: Southwest Jiaotong University Press, 2011:25-68.
[2]	刘爱民. 机车信号的故障分析与处理[J]. 中国新技术新产品, 2018(10):91-92.
	Liu Aimin. Fault analysis and processing of locomotive signal[J]. China New Technology and New Products, 2018(10):91-92.
[3]	甘赟. 图像处理技术的创新应用探索[J]. 信息记录材料, 2021, 22(8):233-235.
	Gan Yun. Exploration on innovative application of image processing technology[J]. Materials for Information Record, 2021, 22(8):233-235.
[4]	De Charette R, Nashashibi F. Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates[C]. Xi'an: Proceedings of the IEEE Intelligent Vehicles Symposium, 2009:358-363.
[5]	Omachi M, Omachi S. Detection of traffic light using structural information[C].Beijing: Proceedings of the IEEE Tenth International Conference on Signal Processing, 2010:809-812.
[6]	Zhu X Y, Zhao C H, Qi X Z, et al. Recognition of traffic lights in urban traffic scenes using color space model[C].Shanghai: Proceedings of the International Conference on Image and Video Processing, and Artificial Intelligence, 2018:1-6.
[7]	Lee E, Kim D. Accurate traffic light detection using deep neural network with focal regression loss[J]. Image and Vision Computing, 2019, 87(7):24-36. doi: 10.1016/j.imavis.2019.04.003
[8]	Beinarovica A, Gorobetz M, Alps I. Algorithms for railway embedded control devices for safety manoeuvres[J]. Electrical, Control and Communication Engineering, 2020, 16(2):95-101. doi: 10.2478/ecce-2020-0014
[9]	张焕增, 李茂强, 刘英杰. 基于视觉的轨道交通信号灯识别算法研究[J]. 电子制作, 2020, 20(18):53-55.
	Zhang Huanzeng, Li Maoqiang, Liu Yingjie. Research on rail transit signal recognition algorithm based on vision[J]. Practical Electronics, 2020, 20(18):53-55.
[10]	中国铁路总公司. 铁路技术管理规程[M]. 北京: 中国铁道出版社, 2014:12-35.
	China Railway Corporation. Railway technical management regulations[M]. Beijing: China Railway Publishing House, 2014:12-35.
[11]	巨志勇, 翟春宇, 张文馨. 基于SVM与区域生长的彩色商品标签图像分割方法[J]. 电子科技, 2021, 34(10):69-74.
	Ju Zhiyong, Zhai Chunyu, Zhang Wenxin. Color commodity label image segmentation method based on SVM and region growth[J]. Electronic Science and Technology, 2021, 34(10):69-74.
[12]	张坤, 李珊珊, 王晓红, 等. 基于机器视觉的铁路信号灯检测技术[J]. 河北工业科技, 2019, 36(2):115-121.
	Zhang Kun, Li Shanshan, Wang Xiaohong, et al. Detection technology of railway signal lamp based on machine vision[J]. Hebei Journal of Industrial Science and Technology, 2019, 36(2):115-121.
[13]	马永杰, 陈振宇, 马芸婷. 基于自适应阈值投影的双行车牌分割方法[J]. 计算机工程与科学, 2020, 42(9):1616-1624.
	Ma Yongjie, Chen Zhenyu, Ma Yunting. A double row license plate segmentation method based on adaptive threshold projection[J]. Computer Engineering and Science, 2020, 42(9):1616-1624.
[14]	胡晨, 胡德敏, 胡钰媛, 等. 一种改进的图像阴影去除方法[J]. 电子科技, 2021, 34(4):41-46.
	Hu Chen, Hu Demin, Hu Yuyuan, et al. An improved image shadow removal method[J]. Electronic Science and Technology, 2021, 34(4):41-46.
[15]	傅迎华, 王雅静, 付东翔, 等. 多算法融合的视盘分割方法[J]. 小型微型计算机系统, 2019, 40(12):2681-2685.
	Fu Yinghua, Wang Yajing, Fu Dongxiang, et al. Multi-algorithm fusion method of optic disc segmentation[J]. Journal of Chinese Computer Systems, 2019, 40(12):2681-2685.
[16]	Widyantoro D H, Saputra K I. Traffic lights detection and recognition based on color segmentation and circle hough transform[C].Yogyakarta: Proceedings of the International Conference on Data and Software Engineering, 2015:237-240.
[17]	董昱, 郭碧. 基于Hu不变矩特征的铁路轨道识别检测算法[J]. 铁道学报, 2018, 40(10):64-70.
	Dong Yu, Guo Bi. Railway track detection algorithm based on Hu invariant moment feature[J]. Journal of the China Railway Society, 2018, 40(10):64-70.
[18]	郭碧, 董昱. 基于分段曲线模型的铁路轨道检测算法[J]. 铁道科学与工程学报, 2017, 14(2):355-363.
	Guo Bi, Dong Yu. Railway track detection algorithm based on piecewise curve model[J]. Journal of Railway Science and Engineering, 2017, 14(2):355-363.
[19]	刘培军, 马明栋, 王得玉. 基于OpenCV图像处理系统的开发与实现[J]. 计算机技术与发展, 2019, 29(3):127-131.
	Liu Peijun, Ma Mingdong, Wang Deyu. Development and implementation of OpenCV-based image processing system[J]. Computer Technology and Development, 2019, 29(3):127-131.
[20]	毛星云, 冷雪飞. OpenCV3编程入门[M]. 北京: 电子工业出版社, 2015:26-59.
	Mao Xingyun, Leng Xuefei. OpenCV3 programming primer[M]. Beijing: Publishing House of Electronics Industry, 2015:26-59.
[21]	李珊珊. 基于机器视觉的铁路信号灯检测与识别技术的研究[D]. 石家庄: 河北科技大学, 2019:7-55.
	Li Shanshan. Research on detection and recognition technology of railway signal light based on machine vision[D]. Shijiazhuang: Hebei University of Science and Technology, 2019:7-55.

	R	G	B
Red	[210, 255]	[0, 90]	[0, 100]
Green	[0, 60]	[200, 255]	[100, 180]
Yellow	[200, 255]	[200, 255]	[50, 120]

	R	G	B
Red	[0, 30]∪[300, 360]	[0, 70]	[0, 90]
Green	[150, 180]	[0, 70]	[0, 90]
Yellow	[80, 140]	[0, 70]	[0, 90]

	样本总数	正确识别总数	错误识别总数	识别正确率/%
一红	30	28	2	93.34
一绿	35	32	3	91.42
一黄	25	22	3	88.12
绿黄	35	33	2	94.28
两绿	35	34	1	96.21
两黄	30	26	4	86.67