基于MeanShift图像分割结合SVM判决的候梯人数视觉检测系统

张宇洋; 刘满华; 韩韬

doi:10.3788/OPE.20132104.1079

您当前的位置：

首页 >

文章列表页 >

基于MeanShift图像分割结合SVM判决的候梯人数视觉检测系统

信息科学 | 更新时间：2020-08-12

- 基于MeanShift图像分割结合SVM判决的候梯人数视觉检测系统
- Elevator-Waiting People Counting System Based on MeanShift Segmentation and SVM Classification
- 光学精密工程 2013年21卷第4期页码：1079-1085
- 作者机构：
  
  上海交通大学电子信息与电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132104.1079
  中图分类号： TP391.4
- 收稿日期：2012-11-30，
  
  修回日期：2012-12-29，
  
  网络出版日期：2013-04-20，
  
  纸质出版日期：2013-04-15
- 稿件说明：
移动端阅览
张宇洋刘满华韩韬. 基于MeanShift图像分割结合SVM判决的候梯人数视觉检测系统[J]. 光学精密工程, 2013,21(4): 1079-1085

ZHANG Yu-Yang LIU Man-hua HAN Tao. Elevator-Waiting People Counting System Based on MeanShift Segmentation and SVM Classification[J]. Editorial Office of Optics and Precision Engineering, 2013,21(4): 1079-1085
张宇洋刘满华韩韬. 基于MeanShift图像分割结合SVM判决的候梯人数视觉检测系统[J]. 光学精密工程, 2013,21(4): 1079-1085 DOI： 10.3788/OPE.20132104.1079.

ZHANG Yu-Yang LIU Man-hua HAN Tao. Elevator-Waiting People Counting System Based on MeanShift Segmentation and SVM Classification[J]. Editorial Office of Optics and Precision Engineering, 2013,21(4): 1079-1085 DOI： 10.3788/OPE.20132104.1079.

摘要

根据电梯群控系统的需求，提出了一种基于视觉检测技术获得候梯人数的新方法。考虑候梯人数检测系统的监测目标为候梯人群，而候梯人群的心理、建筑风格，摄像机的安装角度、复杂背景等因素均会影响到待识别模式的提取，故作者提出了以人体头部作为模式进行模式识别来检测候梯乘客的数量。该方法以Mean Shift图像分割算法和支持向量机(SVM)决策分类器为核心，考虑候梯人群图像采集角度、拍摄镜头的特殊性等对候梯人群头部进行精确识别，较为快速地得到了准确的识别结果。实验证明，该方法处理图像速度可保持在每幅图片2 s以内，准确率超过80%，满足了电梯群控系统的需求。由于能够使电梯群控系统获得稳定可靠的输入参数，从而提高了电梯群的运送效率。

Abstract

According to the requirements of elevator-group-control systems

a new method based on computer vision detection technology was proposed to obtain the number of passengers waiting outside of an elevator. As the detecting target of the system was the passengers waiting outside of the elevator

the feelings of passengers

building styles

the installation angle of a camera and the complex background would effect the detection pattern. Therefore

this paper took the human head as the model to implement the pattern recognition and to detect the number of passengers waiting outside of the elevator. The proposed method based on computer vision detection algorithm combined Mean Shift image segmentation and Support Vector Machine (SVM) classification and recognized the human head features according to the angles of image acquisition and special lenses of cameras. It can obtain accurate recognition results. Experimental results show that the method has an image processing speed by 2 s/image in real time and the accuracy above 80%

which meets the needs of elevator-group-control systems. As a results

the transport efficiency has been improved greatly due to the stable input parameters for the elevator-group-control systems.

关键词

Keywords

references

YANG G Z, HUANG T S. Human face detection in a complex background[J]. Pattern Recognition, 1994, 27(1):53-63.[2]卢春雨, 张长水, 闻芳,等. 基于区域特征的快速人脸检测法[J]. 清华大学学报：自然科学版,1999,39(1):101-105. LU C Y, ZHANG C S, WEN F, et al.. A fast face detection algorithm based on region feature[J]. Journal of Tsinghua University:Science and Technology, 1999,39(1):53-63.(in Chinese)[3]HU Y W, ZHOU P, ZHOU H. A new fast and robust method based on head detection for people-flow counting system[J]. International Journal of Information Engineering, 2001,1:33-43.[4]ZIVKOVIC Z, KROSE B. An EM-like algorithm for color-histogram-based object tracking[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004:798-803.[5]于海滨. 基于头部特征提取的人体检测与跟踪及其应用[D]. 杭州：浙江大学, 2007. YU H B. Real-time human body detection and tracking based on head feature extraction and its application[D]. Hangzhou:Zhejiang University, 2007. (in Chinese)[6]ZHANG E W, CHEN F. A fast and robust people counting method in video surveillance [C]. International Conference on Computational Intelligence and Security, 2007:339-343.[7]YURI B, VLADIMIR K. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J]. IEEE Transactions on PAMI, 2004, 26(9):1124-1137.[8]DORIN C. An algorithm for data-driven bandwidth selection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 24(5):281-288.[9]TAO W B, JIN H, ZHANG Y M. Color image segmentation based on Mean Shift and normalized cuts [J]. IEEE Transactions on Systems, Man, and Cybernetics, 2007,37(5):1382-1389.[10]SYLVAIN P, FREDO D. A topological approach to hierarchical segmentation using Mean Shift[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2007:1-8.[11]孙即祥. 现代模式识别[M]. 北京: 高等教育出版社,2008. SUN J X. Modern Pattern Recognition[M]. Beijing: Higher Education Press, 2008.(in Chinese)[12]SWAIN M J, BALLARD D H. Color Indexing[J]. International Journal of Computer Vision, 2002,7(1):11-32.[13]CANNY J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, 8(6):679-698.[14]AKHIL K, KANCHAN W, Dr. AKHILESH U. Segmentation and counting of people through collaborative augmented environment[J]. Global Journal of Computer Science and Technology, 2011, 11(23):53-57.[15]QING Y. A robust method for counting people in complex indoor spaces [C]. International Conference on Education Technology and Computer (ICETC), 2012:450-454.[16]HYUN H P, HYUNG G L,SEUNG-IN NOH, et al..An area-based decision rule for people-counting systems [J]. Multimedia Content Representation, 2006, 4105:450-457.[17]DJAMEL M, KHEIR-EDDINE A, NICOLAS T. Fast people counting using head detection from skeleton graph [C]. IEEE International Conference on Advanced Video and Signal Based Surveillance, 2012:233-240.[18]KOIVUNEN T A. Noise-insensitive motion detector [J]. IEEE TCE, 1992,38(3):168-174.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

舵类结构件几何量误差视觉检测方法及误差评定