Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network

Bao-qing GUO; Ning WANG

doi:10.3788/OPE.20182612.3040

您当前的位置：

首页 >

文章列表页 >

Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network

Information Sciences | 更新时间：2020-07-05

- Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network
- Optics and Precision Engineering Vol. 26, Issue 12, Pages: 3040-3050(2018)
- 作者机构：
  
  1.北京交通大学机械与电子控制工程学院, 北京 100044
  2.北京交通大学载运工具先进制造与测控技术教育部重点实验室, 北京 100044
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20182612.3040
  CLC： TP391;U216.3
- Received：27 April 2018，
  
  Accepted：17 June 2018，
  
  Published：25 December 2018
- 稿件说明：
移动端阅览
Bao-qing GUO, Ning WANG. Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network[J]. Optics and precision engineering, 2018, 26(12): 3040-3050.
DOI：

Bao-qing GUO, Ning WANG. Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network[J]. Optics and precision engineering, 2018, 26(12): 3040-3050. DOI： 10.3788/OPE.20182612.3040.

摘要

异物侵入铁路限界严重影响行车安全，识别铁路限界内的人员侵入对保证铁路运营安全具有重要意义。由于既有铁路图像异物侵入检测系统只能检测报警图像，无法区分是人员侵入的正确报警还是光线干扰导致的误报警，为了降低上述误报警，本文建立了铁路异物侵限报警样本的训练集和测试集，提出了将改进的深度卷积网络提取的高层Alex特征和HOG特征相结合并用于深度卷积网络模型训练的分类算法。首先引入了改进的AlexNet深度卷积神经网络模型，提取了自动学习的Alex高层特征，然后将其与HOG特征相结合形成Alex-HOG组合特征，最后利用组合特征对分类网络进行训练。铁路异物侵限报警测试样本库的实验表明，该方法对1 498张测试样本图像的识别准确率高达98.46%，时间为3.78 s，实时性和准确率均有较大提高，对降低系统误报率具有重大意义。

Abstract

Objects intruding railway clearance pose great threat to normal railway operations. Identifying intruding pedestrians within the railway clearance limit was of great significance to ensure the safety of railway operations. The existing railway intrusion detection system only detected the intrusion

but did not distinguish whether it was a true alarm of pedestrian intrusion or false alarm caused by light interferences. To reduce false alarms

a training and test set of the alarm image samples were established. A pedestrian classification algorithm based on improved deep convolutional network

trained with combined features of HOG and high-level Alex was then proposed. First

an improved AlexNet deep convolutional neural network model was introduced to extract high-level Alex features by automatic learning; the extracted features were then combined with HOG features to form the combined features of Alex-HOG. Finally

the combined features were used to train the classification network. Experiments on the test set show that the proposed method has a high recognition accuracy of 98.46% in 3.78 s for 1 498 test image samples. The improvements in both accuracy and real-time performance will greatly reduce the false alarm rate of the railway intrusion detection system.

关键词

Keywords

references

董宏辉, 葛大伟, 秦勇等.基于智能视频分析的铁路入侵检测技术研究[J].中国铁道科学, 2010, 31(2):121-125.

DONG H W, GE D W, QIN Y, et al ..Research on railway invasion detection technology based on intelligent video analysis[J].China Railway Science, 2010, 31(2):121-125.(in Chinese)

魏巍.基于立体视觉的异物侵界检测方法研究[D].北京: 北京交通大学, 2014, 12-36. http://cdmd.cnki.com.cn/Article/CDMD-10004-1014178091.htm

WEI W. Research on Method of Intrusion Detection Based on Stereo Vision System [D]. Beijing: Beijing Jiaotong University, 2014, 12-36. (in Chinese)

史红梅, 柴华, 王尧等.基于目标识别与跟踪的嵌入式铁路异物侵限检测算法研究[J].铁道学报, 2015, 37(7):59-65.

SHI H M, CHAI H, WANG Y, et al .. Study on railway embedded detection algorithm for railway intrusion based on object recognition and tracking[J]. Journal Of The China Rallway Society, 2015, 37(7):59-65.(in Chinese)

宁滨, 余祖俊, 朱力强, 等.铁路远程瞭望系统研究与应用[J].铁道学报, 2014.36(12):62-69.

NING B, YU Z J, ZHU L Q, et al ..Remote observation system of railway and its application[J]. Journal of The China Railway Society, 2014.36(12):62-69.(in Chinese)

郭保青, 杨柳旭, 史红梅, 等.基于快速背景差分的高速铁路异物侵入检测算法[J].仪器仪表学报, 2016, 37(6):1371-1378.

Guo B Q, Yang L X, Shi H M, et al .. High-speed railway clearance intrusion detection algorithm with fast background subtraction[J]. Chinese Journal of Scientific Instrument, 2016, 37(6):1371-1378. (in Chinese)

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE . 2005: 886-893. http://www.oalib.com/references/16879692

JIAO JC, WANG X, DENG ZL. Build a robust learning feature descriptor by using a new image visualization method for indoor scenario recognition[J]. Sensors, 2017, 17(7):1569-1585.

黄炎, 范赐恩, 朱秋平, 等.联合梯度直方图和局部二值模式特征的人体检测[J].光学精密工程, 2013, 21(4):1047-1053.

HUANG Y, FAN C E, ZHU Q P, et al .. HOG-LBP pedestrian detection[J]. Opt. Precision Eng., 2013, 21(4):1047-1053. (in Chinese)

SANGEETHA D, DEEPA P. Alow-costand high-performance architecture for robust human detection using histogram of edge oriented gradients[J].Microprocessors And Microsystems, 2017, 53(7):106-119.

IJJINA, E P, MOHAN C K.Hybrid deep neural network model for human action recognition[J]. Applied Soft Computing, 2016, 46(1):936-952.

TIAN Y, GELEMETER J, WANG X, et al .. Lane marking detection via deep convolutional neural network[J].Neurocomputing. 2018, 46:46-55.

刘智, 黄江涛, 冯欣.构建多尺度深度卷积神经网络行为识别模型[J].光学精密工程, 2017, 25(3):799-805.

LIU ZH, HUANG J T, FENG X. Action recognition model construction based on multiscale deep convolution neural network[J]. Opt. Precision Eng., 2017, 25(3):799-805. (in Chinese)

熊昌镇, 单艳梅, 郭芬红.结合主体检测的图像检索方法[J].光学精密工程, 201725(3):792-798.

XIONG CH ZH, SHAN Y M, GUO F H. Accurate image locating combining deep convolution net work with SURF registering[J]. Opt. Precision Eng., 2017, 25(3):792-798. (in Chinese)

刘文祺.基于深度神经网络的铁路异物检测算法[D].北京交通大学, 2016. http://cdmd.cnki.com.cn/Article/CDMD-10004-1016074155.htm

LIU W Q. Railway Obstacle Detection Algorithm Based On Deep Neural Network [D]. Beijing: Beijing Jiaotong University, 2014, 12-36. (in Chinese)

王洋, 余祖俊, 朱力强, 等.基于CNN的高速铁路侵限异物特征快速提取算法[J].仪器仪表学报, 2017, 5(38):1267-1275.

WANG Y, YU Z Y, ZHU L Q, et al .. Fast feature extraction algorithm for high-speed railway clearance intruding objects based on CNN[J]. Chinese Journal of Scientific Instrument, 2017, 5(38):1267-1275. (in Chinese)

RUI T, ZOU J H, ZHOU Y. Pedestrian detection based on multi-convolutional features by feature maps pruning[J]. Multimedia Tools And Applications, 2017, 76(23):25079-25089.

丁文秀, 孙锐, 闫晓星.基于分层深度学习的鲁棒行人分类[J].光电工程. 2015, 42(9):21-27.

DING W X, SUN R, RAN X X. Robust pedestrian classification based on hierarchical deep learning[J].Opto Electronic Engineering, 2015, 42(9):21-27.(in Chinese)

DAE S K. A study of face detection algorithm using CNN with mixed-LGP and hippocampus structure[J]. Journal of Korean Institute of Information Technology. 2018, 16(1):11-17.

Karen Simonyan, Andrew Zisserman. Very deep convolutional networks for large-scale image recognition[C]. International Conference on Learning Representations ( ICLR ), 2015: 1-14. http://cn.bing.com/academic/profile?id=9a83dddfc646cd21a3e38737d303a369&encoded=0&v=paper_preview&mkt=zh-cn

Views

169

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dense pedestrian detection algorithm in multi-branch non-anchor frame network

Lightweight pedestrian detection for multiple scenes

Multispectral pedestrian detection network under modal adaptive weight learning mechanism

Pedestrian detection based on tree-structured graphical model of the human body and hybrid particle swarm clustering

Related Author

LÜ Zhixuan

WEI Xia

HUANG Deqi

Yunzuo ZHANG

Wenbo LI

Wei GUO

Zhouchen SONG

Ying CHEN

Related Institution

School of Electrical Engineering， XinJiang University

School of Information Science and Technology， Shijiazhuang Tiedao University

Key Laboratory of Advanced Process Control for Light Industry， Ministry of Education， Jiangnan University

Faculty of Information Technology, Beijing University of Technolog

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰