[1]邱东,刘德雨.基于模糊深度学习网络的行人检测方法[J].计算机技术与发展,2018,28(10):22-26.[doi:10.3969/ j. issn.1673-629X.2018.10.005]
　QIU Dong,LIU De-yu.A Pedestrian Detection Method Based on Fuzzy Depth Learning Network[J].,2018,28(10):22-26.[doi:10.3969/ j. issn.1673-629X.2018.10.005]
点击复制

基于模糊深度学习网络的行人检测方法()
分享到：

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

卷:
28
期数:
2018年10期
页码:
22-26
栏目:
智能、算法、系统工程
出版日期:
2018-10-10

文章信息/Info

Title:
A Pedestrian Detection Method Based on Fuzzy Depth Learning Network
文章编号:
1673-629X(2018)10-0022-05
作者:
邱东; 刘德雨
长春工业大学 电子与电气工程学院,吉林 长春 130000
Author(s):
QIU Dong; LIU De-yu
School of Electrical and Electronic Engineering,Changchun University of Technology,Changchun 130000,China
关键词:
机器视觉; 多特征; 模糊集; 深度置信网络; 行人检测
Keywords:
machine vision; multi-feature; fuzzy set; depth confidence network; pedestrian detection
分类号:
TP301
DOI:
10.3969/ j. issn.1673-629X.2018.10.005
文献标志码:
A
摘要:
行人检测已经成为机器视觉研究的重要组成部分之一。 深度置信网络(deep belief networks,DBN)优秀的学习能力保证了其学习得到的目标特征更加有效,有利于实现目标的准确检测。 但是传统的深度置信网络模型对整体的目标进行处理,训练时间长,同时需要将所有的样本都进行预先正确的标注,这些都限制了深度置信网络的进一步发展。 对此,文中提出了一种基于多特征的模糊深度置信网络的方法,该方法将经典的深度置信网络与模糊集的理论相结合,融合方向直方图特征对复杂背景下的行人进行检测识别处理。 在静态行人检测库 INRIA 的测试结果表明,该方法在一定程度上减少了训练时间,同时也提高了行人检测的准确率。
Abstract:
Pedestrian detection has become an important part of machine vision research. Deep belief networks (DBN) has excellent learning ability to ensure that the learning of the target features more effective,which is conducive to achieving the goal of accurate detec- tion. However,the traditional deep belief network model deals with the overall goal,which needs a long training time and all the samples need to be correctly labeled at the same time,which are limiting the further development of the deep confidence network. Therefore,we propose a method based on multi-feature fuzzy depth belief network,which combines the classical depth belief network with the theory of fuzzy sets,and the direction histogram features to detect and identify pedestrians in complex background. The test in the static pedestrian detection library INRIA shows that the method not only reduces the training time to a certain extent,but also improves the accuracy of pe- destrian detection.

相似文献/References:

[1]王明平 宋丽梅.基于计算机视觉的车架号采集系统[J].计算机技术与发展,2008,(04):239.
　WANG Ming-ping,SONG Li-mei.Vehicle Identify Number Acquisition System Based on Machine-Vision[J].,2008,(10):239.
[2]蒋恩松 肖辉军 孙刘杰 熊清廉.基于机器视觉的套印误差自动检测系统设计[J].计算机技术与发展,2008,(07):173.
　JIANG En-song,XIAO Hui-jun,SUN Liu-jie,et al.Design of Automatic Detecting Printing Registration Deviation System Based on Machine Vision[J].,2008,(10):173.
[3]李得亮 秦茂玲.一种多特征动态集成的3D模型检索方法[J].计算机技术与发展,2008,(09):30.
　LI De-liang,QIN Mao-ling.3D Model Retrieval Based on Multi- Feature Dynamic Itergration[J].,2008,(10):30.
[4]张锦娟 师军 于佳丽 卢照.SpikeNet的研究及其在快速人脸识别中的应用[J].计算机技术与发展,2010,(07):235.
　ZHANG Jin-juan,SHI Jun,YU Jia-li,et al.Research on SpikeNet and Its Application in Quick Face Recognition[J].,2010,(10):235.
[5]方鹤鹤 冯宏伟 马煜.基于形态滤波和分水岭变换的边缘检测方法[J].计算机技术与发展,2006,(01):49.
　FANG He-he,FENG Hong-wei,MA Yu.Edge Detection Method Based on Morphology Filter and Watershed[J].,2006,(10):49.
[6]李雪晨 汪仁煌 艾星芳.改进的弯曲度算法在阶梯修剪检测中的应用[J].计算机技术与发展,2012,(03):166.
　LI Xue-chen,WANG Ren-huang,AI Xing-fang.Use of Improved Tortuosity Algorithm in Step Form Disfigurement Test[J].,2012,(10):166.
[7]赵立双 冯莹 曹毓.单目视觉定位中SURF算法参数的优化[J].计算机技术与发展,2012,(06):6.
　ZHAO Li-shuang,FENG Ying,CAO Yu.Optimization of SURF Parameters in Monocular Visual Odometry[J].,2012,(10):6.
[8]徐自越 李战明 李二超.OpenCV在焊缝实时检测与处理系统中的应用[J].计算机技术与发展,2012,(08):170.
　XU Zi-yue,LI Zhan-ming,LI Er-chao.Application of OpenCV on Real-time Detection and Processing System of Seam[J].,2012,(10):170.
[9]杨杰,卢盛林,赵晓芳.机器视觉在钢化玻璃缺陷检测中的应用研究[J].计算机技术与发展,2013,(03):211.
　YANG Jie,LU Sheng-lin,ZHAO Xiao-fang.Application and Research of Machine Vision in Tempered Glass Defect Inspection[J].,2013,(10):211.
[10]陈鹏宇[],孙文奇[],赵忠龙[]. 基于机器视觉的印刷质量检测研究[J].计算机技术与发展,2014,24(07):103.
　CHEN Peng-yu[],SUN Wen-qi[],ZHAO Zhong-long[]. rinting Quality Detection Based on Machine Vision[J].,2014,24(10):103.

更新日期/Last Update: 2018-10-10