一种适应光线变化的运动手势检测与跟踪方法

›› 2014, Vol. 27 ›› Issue (4): 154-.

一种适应光线变化的运动手势检测与跟踪方法

李志明,张崎,武霞

(1.北京科技大学计算机与通信工程学院,北京 100083;2.北京科技大学自动化学院,北京 100083)

出版日期:2014-04-15 发布日期:2014-05-14
作者简介:李志明(1989—),男,硕士研究生。研究方向:数字图像处理。E-mail:zhiming_07@126.com。武霞(1988—),女,硕士研究生。研究方向:数字图像处理。张崎(1960—),男,博士,副教授。研究方向:智能交通,数字图像处理,系统工程。

An Algorithm of Good Illumination Robustness for Detecting and Tracking Moving Gestures

LI Zhiming,ZHANG Qi,WU Xia

(1.School of Computer and Communication Engineering,Beijing University of Science and Technology,Beijing 100083,China;2.School of Automation,Beijing University of Science and Technology,Beijing 100083,China)

Online:2014-04-15 Published:2014-05-14

摘要/Abstract

摘要：

在数字图像处理过程中,运动目标的有效检测是一个重要的前提。文中针对现实环境下光线的多变性,提出了一种有效的运动手势检测和跟踪方法。在三帧差法的基础上,结合Camshift运动目标跟踪法、单高斯建模法和自适应阈值提取方法,从而解决了传统帧差法无法适应光线复杂变化的问题。同时,通过使用Camshift跟踪算法对检测出的手势进行跟踪,并实时建立肤色高斯模型自动适应光线的变化以及其光线变化所带来的干扰。经实验表明,该算法可有效检测出运动目标并进行跟踪,另外还可排除光线发生突变所造成的影响。

关键词: 运动手势检测, 适应光线变化, 手势跟踪

Abstract:

In digital image processing,motion target detection is an important premise.An effective moving gesture detection and tracking algorithm is proposed for the variability of light of the actual environment.The three frames difference algorithm is combined with Camshift moving target tracking algorithm,the single Gaussian modeling algorithm and self-adaptive threshold extraction algorithm to solve the problem that traditional frames difference algorithms cannot apply to complex changes in light.The Camshift tracking algorithm is used to track the gesture,and a realtime Gaussian model is built to adapt automatically to the changes in light.Experimental results demonstrate that the algorithm can detect and track the moving gesture and avoid the influence of the changes in light effetely.

Key words: moving gestures detection;good illumination robustness;gesture tracking

中图分类号:

TP391.41

李志明,张崎,武霞. 一种适应光线变化的运动手势检测与跟踪方法[J]. , 2014, 27(4): 154-.

LI Zhiming,ZHANG Qi,WU Xia. An Algorithm of Good Illumination Robustness for Detecting and Tracking Moving Gestures[J]. , 2014, 27(4): 154-.

参考文献

［1］AZAB M M,SHEDEED H A,HUSSEIN A S.A new technique for background modeling and subtraction for motion detection in real-time videos［C］.Los Alamitos:Proceedings of the 17th IEEE International Conference on Image Processing,IEEE Computer Society Press,2010:3453-3456.

［2］HU Weiming,TAN Tieniu,WANG Liang.A survey on visual surveillance of object motion and behaviors［J］.IEEE Transaction on Systems,Man and Cybernetics-Part C,2004,34(3):334-352.

［3］ALVAREZ L,WEICHERT J,SANCHEZ J.Reliable estimation of dense optical flow fields with large displacements［J］.International Journal of Computer Vision,2000,39(1):41-56.

［4］徐凯,陈仕先,颜广.基于高斯模型的运动目标检测方法研究［J］.激光与红外,2012(7):42-45.

［5］JEPSON A D,FLEET D J.Robust online appearance models for visual tracking［J］.IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(10):1296-1311.

［6］尹俊超,刘直芳.基于OpenCV的运动目标检测与跟踪［J］.计算机工程与设计,2011,32(8):2817-2820.

［7］李加佳,彭启民.适应光照突变的运动目标检测算法［J］.计算机辅助设计与图形学学报,2012,24(11):1405-1409.

［8］王江涛.基于视频的目标检测、跟踪及其行为识别研究［D］.南京:南京理工大学,2008.

［9］吕文先,彭启民,吕玉增.光照鲁棒的非线性相关图像匹配方法［J］.计算机辅助设计与图形学学报,2009,21(6):825-830.

［10］CHENG F C,HUANG S C,RUAN S J.Illumination-sensitive background modeling approach for accurate moving object detection［J］.IEEE Transactions on Broadcasting,2011,57(4):794-801.

［11］翁木云,何明一.图像综合特征及其在图像检测与匹配中的应用［J］.中国图象图形学报,2007,12(1):121-126.

［12］丁磊,宫宁生.基于改进的三帧差分法运动目标检测［J］.电视技术,2013(1):151-153.