模式识别与人工智能
2025年4月7日 星期一   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2017, Vol. 30 Issue (7): 588-587    DOI: 10.16451/j.cnki.issn1003-6059.201707002
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于图切割和密度聚类的视频行人检测算法*
曾成斌,刘继乾
贵州理工学院 电气与信息工程学院 贵阳 550000
Pedestrian Detection on Videos Based on Graph Cuts and Density Clustering
ZENG Chengbin, LIU Jiqian
School of Electrical and Information Engineering, Guizhou Institute of Technology, Guiyang 550003

全文: PDF (1400 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 现有视频行人检测方法把行人检测看成一个有监督的两类(即行人和背景)学习问题,区分视频中的行人和背景,并不能很好解决行人的姿态变化和行人间的遮挡问题.文中提出基于图切割和密度聚类的行人检测算法,把行人检测看成一个多类的无监督学习过程.在训练阶段,首先对每个训练样本计算多级梯度方向直方图-局部二分模式(HOG-LBP)特征,然后对多级HOG-LBP特征所属的每个图像块分配不同的权值.为了区别行人的不同部位并赋权值,采用基于图像块的图分割方法从背景中分割行人所在的图像块.最后,再采用基于密度峰值的聚类算法对正样本和负样本分别进行无监督的聚类.在测试阶段,首先通过计算样本特征与每个聚类中心的距离,然后使用前5个最短距离进行投票,判断其是否包含行人.实验证明,文中算法较好解决行人的姿态变化和行人间的遮挡问题,并且随着训练样本的增加,能取得和目前最优行人检测方法可比较的结果.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
曾成斌
刘继乾
关键词 行人检测图切割密度聚类无监督学习    
Abstract:In the existing pedestrian detection algorithms, the pedestrian detection is considered as a supervised learning problem of two classes, pedestrian and background. Thus, the pedestrian and the background in the video are distinguished. However, the problem of variable poses and heavy occlusion can not be solved by these algorithms effectively. In this paper, a pedestrian detection algorithm based on graph cuts and density clustering is proposed. The pedestrian detection is regarded as an unsupervised learning problem of multiple classes. At the training stage, the multilevel histogram of oriented gradient-local binary pattern(HOG-LBP) features are firstly calculated for each of training samples. Then, different weights are assigned to each image block of the multilevel HOG-LBP features. To distinguish the different parts of pedestrian and assign weight, the image sample is segmented by the block-based graph cuts algorithm. Finally, the density clustering approach is used to classify the positive and negative samples into multiple cluster center respectively. At the testing stage, the distance between the multilevel HOG-LBP of test sample and every cluster center is calculated, and the five shortest distances are voted to classify the test sample. Experiments show that the proposed algorithm can handle the pose variations and partial occlusions effectively. Moreover, with the increase of training samples, the results of the proposed algorithm can be comparable to that of the state-of-the-art pedestrian detection algorithms.
Key wordsPedestrian Detection    Graph Cuts    Density Clustering    Unsupervised Learning   
收稿日期: 2017-02-15     
ZTFLH: TP 18  
基金资助:贵州省自然科学基金项目(No.[2014]2081)、贵州省普通高等学校创新团队基金项目(No.[2014]34)资助
作者简介: 曾成斌(通讯作者),男,1979年生,博士,副教授,主要研究方向为行人检测、图像分类.E-mail:cbzeng@qq.com.
刘继乾,男,1979年生,博士,副教授,主要研究方向为图像识别、深度学习.E-mail:Liujiqian@git.edu.cn.
引用本文:   
曾成斌,刘继乾. 基于图切割和密度聚类的视频行人检测算法*[J]. 模式识别与人工智能, 2017, 30(7): 588-587. ZENG Chengbin, LIU Jiqian. Pedestrian Detection on Videos Based on Graph Cuts and Density Clustering. , 2017, 30(7): 588-587.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201707002      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2017/V30/I7/588
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn