基于深度学习的高铁接触网定位器检测与识别

doi:10.3969/j.issn.0253-2778.2017.04.006

中国科学技术大学学报 ›› 2017, Vol. 47 ›› Issue (4): 320-327.DOI: 10.3969/j.issn.0253-2778.2017.04.006

基于深度学习的高铁接触网定位器检测与识别

陈东杰，张文生，杨阳

1. 中国科学院自动化研究所，北京 100190；2. 中国科学院大学，北京 101408

收稿日期:2016-08-28 修回日期:2016-12-08 出版日期:2017-04-30 发布日期:2017-04-30
通讯作者: 张文生
作者简介:陈东杰，男，1990年生，硕士生.研究方向：机器学习与人工智能. E-mail: chendongjie2013@ia.ac.cn
基金资助:
国家自然科学基金(61432008, 61532006, 61472423) 资助.

Detection and recognition of high-speed railway catenary locator based on Deep Learning

CHEN Dongjie, ZHANG Wensheng, YANG Yang

1. Institute of Automation, Chinese Academy of Sciences, Beijing, 100190; 2. University of Chinese Academy of Sciences, Beijing, 101408

Received:2016-08-28 Revised:2016-12-08 Online:2017-04-30 Published:2017-04-30

摘要/Abstract

摘要： 高铁接触网安全监测的主要方法是采用可见光高清相机捕捉接触网零部件的图像序列，通过图像处理和计算机视觉技术实现对零部件的检测、识别与跟踪.在整个监测系统中，定位器检测识别是必要的基础工作.传统的目标检测算法受限于特征描述子的设计，难以依靠人工设计出具有通用性、鲁棒性、高精度的特征描述子.于是提出基于Faster R-CNN模型实现高精度的接触网定位器检测，同时采用Hough变换检测出定位器的骨架轮廓，并通过滤线机制筛选出定位器的最优拟合直线段，为定位器坡度的非接触式精准测量做好基础性工作.

关键词: 定位器, 目标检测, 深度学习, 卷积神经网络, Hough变换

Abstract: High-speed rail monitoring is conducted mainly by adopting image processing and computer vision technology to detect, identify and track catenary components in image sequences taken by the visible light high-definition camera. In the entire monitoring system, the detection and recognition of the locator constitutes the very basis. It is difficult to design the feature descriptor with the characteristics of versatility, robustness and high-accuracy by using traditional target detection algorithms. #br##br#The detection of the high-accuracy locators based on the Faster R-CNN framework has been realized. Meanwhile, the Hough transform is used to detect the skeleton outline of the locator, and the optimal fitting straight line of the locator is extracted by the filtering mechanism, which paves the way for the non-contact precision measurement of the slope of the locators.

Key words: locator, target detection, Deep Learning, convolutional neural networks, Hough transform

中图分类号:

TP391

陈东杰，张文生，杨阳. 基于深度学习的高铁接触网定位器检测与识别[J]. 中国科学技术大学学报, 2017, 47(4): 320-327.

CHEN Dongjie, ZHANG Wensheng, YANG Yang. Detection and recognition of high-speed railway catenary locator based on Deep Learning[J]. Journal of University of Science and Technology of China, 2017, 47(4): 320-327.

参考文献

［1］
张红, 王晓明, 曹洁,等. 基于大数据的智能交通体系架构[J]. 兰州理工大学学报, 2015, 41(2): 112-115.
ZHANG Hong, WANG Xiaoming, CAO Jie, et al. Architecture of intelligent traffic systems based on big data [J]. Journal of Lanzhou University of Technology, 2015, 41(2): 112-115.
[2] 张娟, 毛晓波, 陈铁军. 运动目标跟踪算法研究综述[J]. 计算机应用研究, 2009, 26(12): 4407-4410.
ZHANG Juan, MAO Xiaobo, CHEN Tiejun. Survey of moving object tracking algorithm[J].Computer Application Research, 2009, 26(12): 4407-4410.
[3] LOWE D G. Distinctive image features from scale-invariant key points [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[4] BAY H, TUYTELAARS T, GOOL L V. SURF: Speeded up robust features [J]. Computer Vision & Image Understanding, 2006, 110(3) :404-417.
[5] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE Computer Society, 2005, 1: 886-893.
[6] 范虎伟,卞春华,朱挺,等.非接触式接触网定位器坡度自动检测技术[J].计算机应用, 2010, 30: 102-103.
FAN H W, BIAN C H, ZHU T, et al. Automatic detection of positioning line in contactless overhead contact system[J]. Journal of Computer Applications, 2010, 30: 102-103.
[7] 顾会建. 基于视频图片的接触网定位器识别方法研究[D]. 成都: 西南交通大学, 2014.
[8] 李莹，叶培建，彭兢,等.火星探测出舱机构的识别定位与坡度测量[J]. 宇航学报, 2016, 37(2): 169-174.
LI Ying, YE Peijian, PENG Jing, et al. Egress mechanism recognition and slope measurement for mars exploration [J]. Journal of Astronautics, 2016, 37(2): 169-174.
[9] JADERBERG M, SIMONYAN K, VEDALDI A, et al. Reading text in the wild with convolutional neural networks[J]. International Journal of Computer Vision, 2014, 116(1):1-20.
[10] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE Computer Society, 2014: 580-587.
[11] UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al. Selective search for object recognition [J]. International Journal of Computer Vision, 2013, 104(2): 154-171.
[12] HE K M, ZHANG X, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]// Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: ACM Press, 2014: 346-361.
[13] GIRSHICK R. Fast R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago, USA: IEEE Press, 2015: 1440-1448.
[14] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, arXiv: 1506.01497.
[15] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[16] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[17] HOUGH V, PAUL C. Method and means for recognizing complex patterns, 3069654, US1771560A [P]. 1962.
[18] DUDA R O, HART P E. Use of the Hough transformation to detect lines and curves in pictures [J]. Communications of the ACM, 1972, 15(1): 11-15.
[19] DING L J, GOSHTASBY A. On the canny edge detector[J]. Pattern Recognition, 2001, 34(3):721-725.
[20] JIA Y Q, SHELHAMER E, DONAHUE J, et al. Caffe: Convolutional architecture for fast feature embedding[C]// Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, USA: ACM Press, 2014: 675-678.
[21] Caffe：清晰高效的深度学习(Deep Learning)框架[J/OL]. http://blog.csdn.net/ycheng_sjtu/article/details/39693655.
[22] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645.
[23] OSUNA E, FREUND R, GIROSI F. Training support vector machines: An application to face detection[J/OL]. http://doi.ieeecomputersociety.org/10.1109/CVPR.1997.609310, 2016.06.28.

[1]	魏俣童, 鲍秉坤, 张子祺, 朱进. 不稳定传输中受损视频的低延迟修复方法[J]. 中国科学技术大学学报, 2021, 51(10): 717-724.
[2]	陶陶，柏建树，刘恒，侯书东，郑啸. 基于WGAN反馈的深度学习差分隐私保护方法[J]. 中国科学技术大学学报, 2020, 50(8): 1064-1071.
[3]	李鹏，郑宇，张谈贵. 基于视觉显著性的无人机目标跟踪[J]. 中国科学技术大学学报, 2020, 50(8): 1162-1169.
[4]	王悦，李京. 基于可视化的卷积神经网络优化方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 959-967.
[5]	杜淑颖，杜鹏，丁世飞. 基于CNN的假冒域名识别方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 1019-1025.
[6]	孟徐然，毕秀春，张曙光. 基于生成对抗网络的高频算法及其回测研究[J]. 中国科学技术大学学报, 2020, 50(6): 801-810.
[7]	谷睿哲, 汪平, 郑梦策, 胡红钢, 俞能海. 基于对抗攻击的侧信道防护方案[J]. 中国科学技术大学学报, 2020, 50(10): 1343-1358.
[8]	熊军林, 赵铎. 基于RGB图像的二阶段机器人抓取位置检测方法[J]. 中国科学技术大学学报, 2020, 50(1): 1-10.
[9]	杜炤鑫, 谢海宁, 宋杰, 周德生, 邹晓峰, 陈冉, 曾平. 基于图像处理和深度学习的配网跳闸故障识别方法[J]. 中国科学技术大学学报, 2020, 50(1): 39-48.
[10]	曾伟辉，李淼，张健，黄小平，王敬贤，袁媛. 面向农作物病害识别的高阶残差卷积神经网络研究[J]. 中国科学技术大学学报, 2019, 49(10): 781-790.
[11]	杨子文，陈蕾，浦建宇. 基于两层迁移卷积神经网络的抽象图像情感识别[J]. 中国科学技术大学学报, 2019, 49(1): 40-48.
[12]	孙达昌，毕秀春. 基于深度学习算法的高频交易策略及其盈利能力[J]. 中国科学技术大学学报, 2018, 48(11): 923-932.
[13]	张皓，吴建鑫，. 集成最大汇合: 最大汇合时只有最大值有用吗[J]. 中国科学技术大学学报, 2017, 47(10): 799-807.

基于深度学习的高铁接触网定位器检测与识别

Detection and recognition of high-speed railway catenary locator based on Deep Learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价