首页 | 本学科首页   官方微博 | 高级检索  
     

基于HOG的快速行人计数算法
引用本文:李峰松,张运楚,杨红娟,王业篷.基于HOG的快速行人计数算法[J].计算机系统应用,2014,23(5):172-176.
作者姓名:李峰松  张运楚  杨红娟  王业篷
作者单位:山东建筑大学 信息与电气工程学院, 济南 250101;山东建筑大学 信息与电气工程学院, 济南 250101;山东省智能建筑技术重点实验室, 济南 250101;山东建筑大学 信息与电气工程学院, 济南 250101;山东省智能建筑技术重点实验室, 济南 250101;山东建筑大学 信息与电气工程学院, 济南 250101
基金项目:国家自然科学基金(61303087);住房和城乡建设部科学技术项目(2011-K9-20)
摘    要:为解决智能监控中空间受限情景下的行人计数问题,设计了基于HOG的行人识别与计数算法. 通过限制HOG目标检测算法中图像的缩放范围,并设置感兴趣的检测区域,相比直接应用OpenCV函数实现的目标检测,其时间效率大幅提升;采用基于单计数线算法完成双向流量统计. 三个不同走廊环境的实验表明,本文算法具有不依赖帧间运动信息的特点,可快速稳定的对空间受限情景下的行人进行计数.

关 键 词:智能监控  目标检测  行人计数  HOG
收稿时间:2013/10/9 0:00:00
修稿时间:2013/10/31 0:00:00

Fast Pedestrians Counting Algorithm Based on HOG
LI Feng-Song,ZHANG Yun-Chu,YANG Hong-Juan and WANG Ye-Peng.Fast Pedestrians Counting Algorithm Based on HOG[J].Computer Systems& Applications,2014,23(5):172-176.
Authors:LI Feng-Song  ZHANG Yun-Chu  YANG Hong-Juan and WANG Ye-Peng
Affiliation:School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China;School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China;Shandong Provincial Key Laboratory of Intelligent Buildings Technology, Shandong Jianzhu University, Jinan 250101, China;School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China;Shandong Provincial Key Laboratory of Intelligent Buildings Technology, Shandong Jianzhu University, Jinan 250101, China;School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China
Abstract:A rapid pedestrian detection and counting algorithm based on HOG is proposed for getting the pedestrian flow passing the confined space. The time efficiency is increased remarkable by restricting window shrink range and setting ROI. Counting method based on single line is presented for getting tow directions people number. Experiments in three different passageway show that the proposed method don't depend on moving information, besides it has the ability of fast and stable in confined space pedestrian counting.
Keywords:intelligent monitoring  object detection  pedestrian counting  HOG
本文献已被 CNKI 等数据库收录!
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号