[1]刘磊,陈泽虹,张勇,等.深度图像下基于头部多特征的人数统计算法[J].深圳大学学报理工版,2017,34(6):584-590.[doi:10.3724/SP.J.1249.2017.06584]
　Liu Lei,Chen Zehong,Zhang Yong,et al.A people counting algorithm based on multi-feature of head region in depth images[J].Journal of Shenzhen University Science and Engineering,2017,34(6):584-590.[doi:10.3724/SP.J.1249.2017.06584]
点击复制

深度图像下基于头部多特征的人数统计算法()
分享到：

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第34卷
期数:
2017年第6期
页码:
584-590
栏目:
电子与信息科学
出版日期:
2017-11-20

文章信息/Info

Title:
A people counting algorithm based on multi-feature of head region in depth images
文章编号:
201706006
作者:
刘磊1; 陈泽虹2; 张勇1; 赵东宁2; 3
1）深圳大学ATR国防科技重点实验室, 广东深圳518060
2）深圳大学信息工程学院, 广东深圳518060
3）哈尔滨工业大学（深圳）计算机科学与技术学院，广东深圳 518055
Author(s):
Liu Lei1;  Chen Zehong2;  Zhang Yong1;  and Zhao Dongning2; 3
1) ATR Key Laboratory of National Defense Technology, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
2) College of Information Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
3) School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, Guangdong Province, P.R.China
关键词:
数字图像处理; 深度图像; 区域生长; Kalman滤波; 多特征; 人数统计
Keywords:
digital image processing;  depth image;  region growing;  Kalman filter;  multi-feature;  people counting
分类号:
TP 319
DOI:
10.3724/SP.J.1249.2017.06584
文献标志码:
A
摘要:
在现实生活中，因人流量过大而引发的安全事故不胜枚举．为了防止此类事故的发生，可通过视频监控的方式统计人数，及时对行人进行限流和分流．提出一种有效的人数统计算法．该算法采用深度摄像机作为视频采集源，通过分析和提取深度图像下头部的4个特征，实现行人头部检测，并依靠Kalman滤波技术实现对头部目标的跟踪，进而达到人数统计的目的．该算法对行人的不同发型具有一定适应性，同时对轻微遮挡和多人环境下的头部检测均有良好效果．该算法人数统计平均准确率达到88.6%．
Abstract:
In daily life, a great number of security accidents are caused by the excessive flow of people. In order to prevent the occurrence of such accidents, we propose an efficient algorithm to count the number of people by using video monitors and limit the flow of people in time. The algorithm uses the depth camera as a video capture device and realizes the detection of people’s heads by analyzing and extracting the four features of heads in depth image. The method uses Kalman filter technology to track the head and achieves the purpose of counting statistics. The proposed algorithm can effectively solve the head detection problem of complex scenes, such as hairstyle diversity and head part-occlusion. The average accuracy of the proposed algorithm reaches about 88.6%.

参考文献/References:

［1］ 孙棣华, 闫川, 赵敏, 等. 结合梯度与彩色直方图的人头识别［J］. 重庆工学院学报自然科学, 2007, 21(12): 1-5.
Sun Dihua, Yan Chuan, Zhao Min, et al. Head detection based on gray gradient and color histogram［J］. Journal of Chongqing Institute of Technology, 2007, 21(12): 1-5.(in Chinese)
［2］ Gardel A, Bravo I, Jimenez P, et al. Real time head detection for embedded vision modules［C］// IEEE International Symposium on Intelligent Signal Processing. San Diego, USA: IEEE Computer Society, 2007:1-6.
［3］ Chen Juan, Wen Quan, Zhuo Chenglong, et al. Automatic head detection for passenger flow analysis in bus surveillance videos［C］// International Conference on Image and Signal Processing. San Diego, USA: IEEE Computer Society, 2012:143-147.
［4］ Chua J L, Chang Y C, Lim W K. Visual based fall detection through human shape variation and head detection［C］// International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT). San Diego, USA: IEEE Computer Society, 2014: 61-65.
［5］ Sim C H, Rajmadhan E, Ranganath S. Using color bin images for crowd detections［C］// IEEE International Conference on Image Processing. San Diego, USA: IEEE Computer Society, 2008:1468-1471.
［6］ Luo Jun, Wang Jinqiao, Xu Huazhong, et al. Real-time people counting for indoor scenes［J］. Signal Processing, 2015,124:27-35.
［7］ Cai Zebin, Yu Zhuliang, Liu Hao, et al. Counting people in crowded scenes by video analyzing［C］// IEEE Conference on Industrial Electronics and Applications. San Diego, USA: IEEE Computer Society, 2014:1841-1845.
［8］ Gao Chenqiang, Li Pei, Zhang Yajun, et al. People counting based on head detection combining Adaboost and CNN in crowded surveillance environment［J］. Neurocomputing, 2016, 208:108-116.
［9］ Aziz K, Merad D, Iguernaissi R, et al. Head detection based on skeleton graph method for counting people in crowded environments［J］. Journal of Electronic Imaging, 2016, 25(1): 013012-013025.
［10］ Zhang Xucong, Yan Junjie, Feng Shikun, et al. Water filling: unsupervised people counting via vertical Kinect sensor［C］// IEEE the 9th International Conference on Advanced Video and Signal-Based Surveillance. San Diego, USA: IEEE Computer Society, 2012:215-220.
［11］ Gao Chenqiang, Liu Jun, Feng Qi, et al. People-flow counting in complex environments by combining depth and color information［J］. Multimedia Tools and Applications, 2016, 75(15):1-17.
［12］ Coskun A, Kara A, Parlaktuna M, et al. People counting system by using Kinect sensor［C］// International Symposium on Innovations in Intelligent Systems and Applications. San Diego, USA: IEEE Computer Society, 2015, 1-7.
［13］ Rauter M. Reliable human detection and tracking in top-view depth images［C］// International Conference on Computer Vision and Pattern Recognition Workshops. San Diego, USA: IEEE Computer Society, 2013:529-534.
［14］ Vera P, Zenteno D, Salas J. Counting pedestrians in bidirectional scenarios using zenithal depth images［C］// Mexican Conference on Pattern Recognition. New York, USA: Springer-Verlag, 2013:84-93.
［15］ Oosterhout T V, Bakkes S, Krse B J A. Head detection in stereo data for people counting and segmentation［C］// Visapp-Sixth International Conference on Computer Vision Theory & Applications. Algarve, Portugal:［s. n.］, 2011:470-479.
［16］ Oosterhout T V, Englebienne G, Krse B. RARE: people detection in crowded passages by range image reconstruction［J］. Machine Vision and Applications, 2015, 26(5):561-573.
［17］ Galcˇík F, Gargalík R. Real-time depth map based people counting［C］// International Conference on Advanced Concepts for Intelligent Vision Systems. New York, USA: Springer-Verlag, 2013:330-341.
［18］ 王江峰. 基于轨迹片段关联的目标跟踪与事件检测方法研究［D］. 长沙: 国防科学技术大学, 2011.
Wang Jiangfeng. Researches on object tracking and event detection based on tracklet association［D］. Changsha: National University of Defense Technology, 2011.(in Chinese)
［19］ Chen C, Chang Y, Chen T, et al. People counting system for getting in/out of a bus based on video processing［C］// The Eighth International Conference on Intelligent Systems Design and Applications. Kaohsiung, China: IEEE Computer Society, 2008:565-569.
［20］ Ristic B, Arulampalam S, Gordon N. Beyond the Kalman filter: particle filter for tracking application［J］. IEEE Transactions of Aerospace & Electronic Systems, 2004, 19(7): 37-38.

备注/Memo

备注/Memo:
Received：2016-12-20；Revised：2017-05-15；Accepted：2017-07-14
Foundation：Natural Science Foundation of Guangdong Province (2015A030310172); Science and Technology Plan Projects of Shenzhen ( JCYJ20170302145623566, JCYJ20160331185006518)
Corresponding author：Doctor Zhao Dongning. E-mail:582101@qq.com
Citation：Liu Lei, Chen Zehong, Zhang Yong, et al. A people counting algorithm based on multi-feature of head region in depth images［J］. Journal of Shenzhen University Science and Engineering, 2017, 34(6): 584-590.（in Chinese）
基金项目：广东省自然科学基金资助项目（2015A030310172）；深圳市科技计划资助项目（JCYJ20170302145623566, JCYJ20160331185006518）
作者简介：刘 磊(1991—)，男，深圳大学硕士研究生．研究方向：图像处理．E-mail：270568577@qq.com
引文：刘磊，陈泽虹，张勇，等．深度图像下基于头部多特征的人数统计算法［J］. 深圳大学学报理工版，2017，34(6)：584-590.
更新日期/Last Update: 2017-10-10