摘要
本文研究了基于指端标记的视频手指定位技术,在不影响正常操作的触觉及力反馈的同时,准确定位手指空间位置为人机交互提供基础。
本文侧重二维手部跟踪与指尖中心定位的研究,系统基于PC平台,选择DirectShow开发包作为系统开发工具。软件采用模块化的设计思想,在DirectShow框架下实现了视频采集、手部跟踪、指尖中心定位等模块。
首先对运动跟踪中常用的基于帧差的检测及跟踪,基于减背景的检测及跟踪以及基于肤色的跟踪分别进行比较,最终选取基于目标颜色特征的Camshift算法对手部进行跟踪。为解决当目标运动情况复杂或发生遮挡时跟踪失败的问题,本文提出CamShift和卡尔曼滤波器相结合的算法。同时本文还提出了当跟踪丢失时的搜索框重置以及用户肤色标定等改进方法。经实验证明,改进后的算法具有较强的鲁棒性和实用性。
指端中心定位部分,本文以彩色标记区分不同的手指,既降低了识别难度又避免了复杂的特征匹配过程,提高了整体定位速度。算法摒弃受光照影响大的RGB颜色空间,在YIQ、HIS两个空间做对比实验,最终选取具有较强可靠性的YIQ颜色空间进行指端定位。
This paper proposes a new finger tracking method with video based on colored markers on fingertips.This method will not affect the feeling and force feedback while tracking the fingers. It is hoped to accomplish the tracking function instead of data glove.
The architecture development is based on Direct X standard.This system implements the functions of video acquiring,hand detecting and tracking,centre fingertips tracking,which finally realizes an intelligent system with video finger tracking research based on colored markers on fingertips.
The experimental results of frame difference, object's color character and background subtraction are compared as well as their advantages and disadvantages are analyzed.On the hand tracking research,the CamShift algorithm which means Continuous Adaptive Mean-Shift is mainly discussed. While Camshift is a tracking method based on the object's color character,and it is widely used for the parameter-less and fast calculation.CamShift algorithm works well in the simple background,but not in the complicated background. So the CamShift algorithm combined with Kalman filter is proposed in my paper. Kalman filter is used to forecast possible position of target, then Camshift search the real position near the possible position. The algorithm has good effect to moving target in the complicated background,and can deal well with simple occultation.Then search-window re-assignment and auto-CamShift are proposed.The results proved that the algorithm is robust and practical.
In the fingers tracking,the method of dividing different fingers with colored markers on fingertips is proposed. Besides the reduction of identifying difficulty, it passes over the complicated process of character matching. Different color space,for example YIQ,HIS,is experimented. And YIQ was chose for good result.
引文
[1]董士海.人机交互的进展及面临的挑战[J].计算机辅助设计与图形学学报,2004,16(1):1~13.
[2]雷超,戴国忠.三维交互体系结构的研究与实现[J].计算机研究与发展,2001,38(5):557~56.
[3] M Rauterberg,M Bichsel,M Meier,M Fjeld.A gesture based interaction technique for a planning tool for construction and design.IEEE International Workshop on Robot and Human Communication,1997.
[4] Fels S S,Hinton G E.Glove-Talk:a neural network interface between a data-glove and a speech synthesizer.IEEE Transactions on Neural Networks,Vol.4,No.1,1993:2~8.
[5] Sturman D J,Zeltzer D.A survey of glove-based input Computer Graphics and Applications. IEEE,Vol.14,No.1,1994:30~39.
[6]王家顺,王田苗,魏军,等.一种面向遥操作的新型数据手套研制[J].机器人(ROBOT) , 2000, 22(3):201~206.
[7]黄天智,刘越,王涌天.用于圆明园数字重建的定点式户外增强现实系统[C].第四届全国虚拟现实与可视化学术会议论文集,2004(8):610~615.
[8]陆其明.DirectShow实务精选[M].北京:科学出版社,2004.
[9]阮新新主编.多媒体技术与应用[M] .北京:清华大学出版社,2006.
[10]陆其明.DirectShow开发指南[M].北京:清华大学出版社,2003:166~194.
[11]潘爱民.COM原理与应用[M].北京:清华大学出版社,1999.
[12] Dale Rogerson.COM技术内幕[M].北京:清华大学出版社,1999.
[13]刘瑞祯,于仕琪.OpenCV教程基础篇[M].北京:北京航空航天大学出版社,2007.
[14] Rehg J M, Kanade T. Digit Eyes:Vision-based Hand Tracking for Human-computer Interaction. IEEE Workshop on Motion of Non-Rigid and Articulated Objects,1994:16~22.
[15] Jianchao Zeng,Yue Wang,Matthew Freedman.Color-Feature-Based Finger Tracking for Breast Palpation Quantification,Proceedings of the 1997 IEEE,International Conference on Robotics and Automation.
[16] Wayne Piekarski,Ross Smith,Grant Wigley,etal.Mobile Hand Tracking Using FPGAs for Low Powered Augmented Reality,Proceedings of the Eighth International Symposium on Wearable Computers (ISWC’04).
[17] Heap T,Hogg D.Towards 3D Hand Tracking Using a Deformable Model.The Second International Conference on Automatic Face and Gesture Recognition,1996:140~145.
[18] Stauffer C,Grimson W.Adaptive background mixture models for real-time tracking [C].In:Proc IEEE Conference on Computer Vision and Pattern Recognition,For Collins,Colorado,1999,2, pp:246~252.
[19] Lipton A,Fujiyoshi H,Patil R.Moving target classification and tracking form real- time video. In:Proc IEEE Workshop on Applications of Computer Vision,NJ,1998:8~14.
[20] Collins Ret al.A system for video surveyllance and monitoring:VSAM final report.Carnegie Mellon University,Technical Report:CMU-RI-TR-00-12,2000.
[21] Elgammal A,et al.Non-parametric Model for Background Subtraction.European Conference on Computer Vision,2002.
[22] Rein-Lien Hsu,Mohamed Abdel-Mottaleb,Anil K. Jain.Face Detection in Color Image.IEEE Trans.Pattern Analysis and Machine Intelligence,2002,24(5):696~706.
[23] Cary. Bradski.Computer Vision Face Tracking as a Component of a Perceptual User Interface[J] .Proc. IEEE Workshop Applications of Computer Vision,1998,(10):214~219.
[24] Fukanaga K,Hostetler L D.The estimation of the gradient of a density function,with applications in pattern recognition [J].IEEE Trans Information Theory,1975,21(1):32~40.
[25] Cheng Yizong.Mean shift mode seeking and clustering [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1995,17(8):790~799.
[26] Comaniciu D,Meer P.Mean Shift Analysis and Application[A].In:Proc of the 7th IEEE International Conference on Computer Vision [C],Kerkyra,Greece:IEEE Computer Society Press,1999:1197~1203.
[27] Comaniciu D,Meer P.Mean Shift:A Robust application toward feature space analysis [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2002,24(5):603~619.
[28] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25 (5):564~575.
[29] R.E.Kalman.A New Approach to Linear Filtering and Prediction Problems,Trans.Of ASME, Journal of Basic Engineering[C],82S(3),1960:34~45.
[30] D.Comaniciu,V.Ramesh,P.Meer.Real-Time Tracking of non-rigid Objects using Mean Shift [C], Proc. IEEE Conf. Computer Vision and Pattern Recognition,vo1.2,pp:142~149,June 2000.
[31] Grewal,Mohinder S. and Angus P. Andrews.Kalman Filtering Theory and Practice[M].Upper Saddle River,NJ USA,Prentice Hall,1993.
[32] Welch and Bishop.An introduction to the Kalman Filter[J].UNC-Chapel Hill,TR95-041,Apri15,2004.
[33]求是科技.数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006:471~477.
