[1]张 剑,王等准,莫光健,等.基于改进 YOLOv3 的高铁异物入侵检测算法[J].计算机技术与发展,2022,32(02):69-74.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 011]
　ZHANG Jian,WANG Deng-zhun,MO Guang-jian,et al.High-speed Rail Foreign Body Intrusion Detection Algorithm Based on Improved YOLOv3[J].,2022,32(02):69-74.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 011]
点击复制

基于改进 YOLOv3 的高铁异物入侵检测算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年02期
页码:
69-74
栏目:
图形与图像
出版日期:
2022-02-10

文章信息/Info

Title:
High-speed Rail Foreign Body Intrusion Detection Algorithm Based on Improved YOLOv3
文章编号:
1673-629X(2022)02-0069-06
作者:
张 剑1 ; 王等准1 ; 莫光健2 ; 谢本亮1*
1. 贵州大学 大数据与信息工程学院 半导体功率器件可靠性教育部工程研究中心微纳电子与软件技术重点实验室,贵州 贵阳 550025;
2. 成都铁路公安局贵阳公安处,贵州 贵阳 550025
Author(s):
ZHANG Jian1 ; WANG Deng-zhun1 ; MO Guang-jian2 ; XIE Ben-liang1 *
1. Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province,Power Semiconductor Device Reliability Engineering Center of Ministry of Education,School of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China;
2. Guiyang Public Security Division,Chengdu Railway Public Security Bureau,Guiyang 550025,China
关键词:
目标检测; 高铁异物检测; YOLOv3; 可切换空洞卷积; 多尺度预测
Keywords:
×object detection; high-speed rail foreign body detection; YOLOv3; switchable atrous convolution; multi-scale prediction××××
分类号:
TP391. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 011
摘要:
针对传统铁路异物检测方法中实时性不高、检测精度不够的问题,提出一种基于 YOLOv3 网络的高铁异物入侵的检测算法。 为提高 YOLOv3 网络对图片特征的利用能力,利用可切换空洞卷积替代特征提取网络中的前四个 3×3 卷积,增加了卷积的感受野。 然后为提升小物体检测精度,改进 FPN 结构,从 YOLOv3 特征提取网络中第二次下采样输出的特征图建立 104×104 作为第四个尺度预测。 通过在高铁异物检测数据集上的实验表明,改进后的 YOLOv3 高铁异物检测网络在检测速度稍降的情况下,平均检测精度达到 79. 1% ,比原网络增加 4. 3% 。 改进 YOLOv3 高铁异物入侵检测网络能够提升不同尺度目标的检测精度,同时相较于其他目标检测网络有更好的检测精度与实时性。
Abstract:
Aiming at the problems of low real-time performance and insufficient detection accuracy in traditional railway foreign body detection methods,a high-speed rail foreign body intrusion detection algorithm based on YOLOv3 network is proposed. In order to improvethe detection accuracy of YOLOv3 on various scales,the first four 3*3 convolutions in the feature extraction network are replaced by theSAC,which increases the reception field of the convolution. Then,in order to improve the detection accuracy of small objects,the FPNstructure is improved, and 104*104 is established as the fourth scale prediction from the feature graph output from the seconddownsampling in the YOLOv3 feature extraction network. Experiments on the high-speed rail foreign body detection data set show thatthe improved YOLOv3 high - speed rail foreign body detection network achieves an average detection accuracy of 79. 1% under thecondition of slightly reduced detection speed,which is 4. 3% higher than the original network. The improved YOLOv3 high-speed railforeign body detection network can improve the detection accuracy of targets of different scales,and has better detection accuracy and real-time performance compared with other target detection networks.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(02):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(02):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(02):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(02):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(02):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(02):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(02):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(02):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(02):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(02):36.

更新日期/Last Update: 2022-02-10