|本期目录/Table of Contents|

[1]苏 杨,卢 翔,李 琨,等.基于轻量深度学习网络的机房人物检测研究[J].工业仪表与自动化装置,2021,(01):100-103.[doi:1000-0682(2021)01-0000-00]
　SU Yang,LU Xiang,LI Kun,et al.Research on computer room human detection based on lightweight deep learning network[J].Industrial Instrumentation & Automation,2021,(01):100-103.[doi:1000-0682(2021)01-0000-00]
点击复制

基于轻量深度学习网络的机房人物检测研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年01期
页码:
100-103
栏目:
出版日期:
2021-02-15

文章信息/Info

Title:
Research on computer room human detection based on lightweight deep learning network
作者:
苏 杨1; 卢 翔1; 李 琨1; 张少超2
1.贵州电网有限责任公司 信息中心；
2.贵州大学 机械工程学院，贵州 贵阳 550002
Author(s):
SU Yang1; LU Xiang1; LI Kun1; ZHANG Shaochao2
1.Information Center of Guizhou Power Grid Co., Ltd.;?div>2. Mechanical Engineering of Guizhou University, Guizhou Guiyang 550002, China
关键词:
人物检测; 深度学习; 特征提取; 特征金字塔
Keywords:
human detection;  deep learning;  feature extraction;  feature pyramid
分类号:
TP391
DOI:
1000-0682(2021)01-0000-00
文献标志码:
A
摘要:
机房内的服务器受到破坏、信息泄露等问题时将对电网系统造成不可逆转的损失。该文提出一种基于轻量级深度学习网络的机房人物检测方法，以实时提醒管理人员监控视频中的异常信息。该方法以MobileNet作为特征提取网络，并调整SSD中的特征金字塔结构使其更适应于机房环境中的人物检测。以某电网系统机房为平台进行检测实验，结果表明，该方法较好地完成了机房人物检测任务，满足对视频流分析时的精度及实时性需求。
Abstract:
When the server in the computer room is damaged,information leakage and other problems will cause irreversible loss to the power grid system.This paper proposes a method of computer room character detection based on lightweight deep learning network to remind managers of abnormal information in monitoring video in real time.This method uses MobileNet as the feature extraction network, and adjusts the feature pyramid structure of SSD to make it more suitable for human detection in the computer room environment.The test experiment is carried out on the platform of a power system computer room.The results show that the method can complete the task of human detection in computer room,and meet the needs of accuracy and real-time in video stream analysis.

参考文献/References:

[1] 周昊飞,刘玉敏.基于小波重构的动态过程LSSVM- BPNN在线智能监控模型[J].系统管理学报,2018,27(02): 291-298.

[2] WU D, ZHANG J.Personnel intrusion detection in the complex environment of mine[C]//2018 International Conference on Sensor Networks and Signal Processing (SNSP), IEEE Computer Society, 2018:231 -235.?/div>
[3] 苑洋,黄迪,王蕴红.面向不同距离的实时人体检测与跟踪系统[J].模式识别与人工智能,2014,27(10):939-945.
[4] 金炳瑞.基于图像处理的铁路轨道异物入侵的自动识别研究[D].兰州:兰州交通大学,2016.
[5] 卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016,31(01):1-17.
[6] 李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(09):2508-2515.
[7] LECUN Y, BENGIO Y, HINYON G. Deep learning[J]. nature, 2015, 521(7553): 436.
[8] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J].Medical image analysis, 2017, 42: 60-88.
[9] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. 2017.
[10] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//European Conference on Computer Vision (ECCV),2016, 2016:21-37.
[11] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// International Conference on Machine Learning. Cambridge, USA: JMLR, 2015:448-456.
[12] ISLAM M A, AKHTER S, MURSALIN T E, et al. A suitable neural network to detect textile defect[C]//International Conference on Neural Information Processing. Springer, Berlin, Heidelberg, 2006: 430 -438.
[13] XIE Liang jun, HUANG Rui, GU Nong, et al. A novel defect detection and identification method in optical inspection [J].Neural Computing and Applications,2014,24(8): 1953-1962.

相似文献/References:

[1]杨 帅,张有芬,李玉惠,等.基于深度卷积神经网络的车标分类[J].工业仪表与自动化装置,2017,(05):75.
　YANG Shuai,ZHANG Youfen,LI Yuhui,et al.Vehicle classification based on deep convolutional neural network[J].Industrial Instrumentation & Automation,2017,(01):75.
[2]徐先峰,黄刘洋,龚 美.基于卷积神经网络与双向长短时记忆网络组合模型的短时交通流预测[J].工业仪表与自动化装置,2020,(01):13.
　XU Xianfeng,HUANG Liuyang,GONG Mei.Short-term traffic flow prediction based on combined model of convolutional neural network and bidirectional long-term memory network[J].Industrial Instrumentation & Automation,2020,(01):13.
[3]张晓华,马 煜,杨晨辉,等.基于卷积神经网络的设备安装位置智能识别方法[J].工业仪表与自动化装置,2021,(01):13.[doi:1000-0682(2021)01-0000-00]
　ZHANG Xiaohua,MA yu,YANG Chenhui,et al.Intelligent identification method of equipment installation position based on convolution neural network[J].Industrial Instrumentation & Automation,2021,(01):13.[doi:1000-0682(2021)01-0000-00]

备注/Memo

备注/Memo:
收稿日期：2020-06-30
作者简介：
苏杨（1983），男，硕士研究生，高级工程师，研究方向为信息化发展。
更新日期/Last Update: 1900-01-01