Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (8): 2324-2329.DOI: 10.11772/j.issn.1001-9081.2021030385

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Detection of left and right railway tracks based on deep convolutional neural network and clustering

ZENG Xiangyin, ZHENG Bochuan, LIU Dan   

  1. School of Computer Science, China West Normal University, Nanchong Sichuan 637002, China
  • Received:2021-03-15 Revised:2021-05-10 Online:2021-08-10 Published:2021-07-12
  • Supported by:
    This work is partially supported by the Fundamental Research Funds of West China Normal University (19B045).


曾祥银, 郑伯川, 刘丹   

  1. 西华师范大学 计算机学院, 四川 南充 637002
  • 通讯作者: 郑伯川
  • 作者简介:曾祥银(1994-),男,四川大竹人,硕士研究生,CCF会员,主要研究方向:机器学习、深度学习;郑伯川(1974-),男,四川自贡人,教授,博士,CCF会员,主要研究方向:机器学习、深度学习、计算机视觉;刘丹(1996-),女,四川广安人,硕士研究生,CCF会员,主要研究方向:深度学习、目标检测。
  • 基金资助:

Abstract: In order to improve the accuracy and speed of railway track detection, a new method of detecting left and right railway tracks based on deep Convolutional Neural Network (CNN) and clustering was proposed. Firstly, the labeled images in the dataset were processed, each origin labeled image was divided into many grids uniformly, and the railway track information in each grid region was represented by one pixel, so as to construct the reduced images of railway track labeled images. Secondly, based on the reduced labeled images, a new deep CNN for railway track detection was proposed. Finally, a clustering method was proposed to distinguish left and right railway tracks. The proposed left and right railway track detection method can reach accuracy of 96% and speed of 155 frame/s on images with size of 1000 pixel×1000 pixel. Experimental results demonstrate that the proposed method not only has high detection accuracy, but also has fast detection speed.

Key words: railway track detection, grid segmentation, Convolutional Neural Network (CNN), clustering, foreign object intrusion, lane detection

摘要: 为了提高铁路轨道线检测的准确率和速度,提出了一种基于深度卷积神经网络(CNN)和聚类的左右轨道线检测方法。首先,处理数据集的标注图像,将原标注图均匀分割成许多网格,每个网格局部区域的轨道线信息用一个像素点代替,从而构成缩小的轨道线标注图;然后,基于缩小后的轨道线标注图,提出了一种新的深度CNN用于轨道线检测;最后,提出一种聚类方法来区分左右轨道线。对于长宽都为1 000像素大小的图片,所提左右轨道线检测方法的检测速度达到155 frame/s,准确率达到96%。实验结果表明,所提方法不仅检测准确率高,而且检测速度快。

关键词: 轨道线检测, 网格分割, 卷积神经网络, 聚类, 异物侵限, 车道线检测

CLC Number: