一种基于高频率投影仪—摄像头的人机交互系统
|
摘要
针对桌面投影设备,提出了一种基于单投影仪—单摄像头的人机交互系统架构,可以实现在投影面上的类触摸屏操作。提出了一种基于高速投影中互补阴影的方法,在不影响使用者视觉体验的前提下实现触碰点位置检测与触碰判断。针对低强度差分阴影的提取,提出了基于马尔可夫随机场模型的最优化方法,提高了复杂环境噪声下阴影分割的鲁棒性。针对指尖检测,使用了一种基于最小二乘法的曲率估计方法,提高了触碰定位的准确度;触碰判断方面,提出了一种基于双目约束与几何模型的高精度触碰判断准则。实验证明,系统达到触碰识别率99.2%,误识别率0.6%,像素级的触碰点判断准确率1.77像素,超过了同类研究的最先进水平,能够在PC机上达到60 fps的运行速度,这满足了绝大部分实时应用的需求。
This paper proposed a novel projector-camera based human-computer interaction system for touch-pad application of tabletop projection. Taking the advantage of differential shadow in high-frequency projection,the system realized the localization and judgment of touch action without influencing users' visual experience. A Markov random field based shadow segmentation method helped to robustly extract the low-intensity shadow under complex environment. To precisely locate fingertip,the algorithm searched along the contour of the shadow and used a least square method to estimate the curvature of the shadow contour.Furthermore,the binocular constraint and geometrical model based touch judging method helped to raise the touch judging precision in the system. The experiment shows that the proposed system performs better than state-of-art works,with touch recognition rate at 99. 2%,false alert rate at 0. 6% and touch localization accuracy at 1. 77 pixels. Meanwhile,the system works at 60 fps on a conventional PC,which satisfies the requirement of most of real-time applications.
This paper proposed a novel projector-camera based human-computer interaction system for touch-pad application of tabletop projection. Taking the advantage of differential shadow in high-frequency projection,the system realized the localization and judgment of touch action without influencing users' visual experience. A Markov random field based shadow segmentation method helped to robustly extract the low-intensity shadow under complex environment. To precisely locate fingertip,the algorithm searched along the contour of the shadow and used a least square method to estimate the curvature of the shadow contour.Furthermore,the binocular constraint and geometrical model based touch judging method helped to raise the touch judging precision in the system. The experiment shows that the proposed system performs better than state-of-art works,with touch recognition rate at 99. 2%,false alert rate at 0. 6% and touch localization accuracy at 1. 77 pixels. Meanwhile,the system works at 60 fps on a conventional PC,which satisfies the requirement of most of real-time applications.
引文
[1]Wilson A D.Play Anywhere:a compact interactive tabletop projectionvision system[C]//Proc of the 18th Annual ACM Symposium on User Interface Software and Technology.New York:ACM Press,2005:83-92.
[2]Harrison C,Benko H,Wilson A D.Omni Touch:wearable multitouch interaction everywhere[C]//Proc of the 24th Annual ACM Symposium on User Interface Software and Technology.New York:ACM Press,2011:441-450.
[3]Hu Jun,Li Guolin,Xie Xiang,et al.Bare-fingers touch detection by the button’s distortion in a projector-camera system[J].IEEE Trans on Circuits&Systems for Video Technology,2013,24(4):566-575.
[4]Dai J,Chung C K R.Touchscreen Everywhere:on transferring a normal planar surface to a touch-sensitive display[J].IEEE Trans on Cybernetics,2013,44(8):1383-1396.
[5]Park H,Seo B,Park J.Subjective evaluation on visual perceptibility of embedding complementary patterns for nonintrusive projection-based augmented reality[J].IEEE Trans on Circuits&Systems for Video Technology,2010,20(5):687-696.
[6]Song Wei,Xie Xiang,Li Guolin,et al.Flexible method to calibrate projector-camera systems with high accuracy[J].Electronics Letters,2015,50(23):1685-1687.
[7]Cai Xilei,Xie Xiang,Li Guolin,et al.A new method of detecting fingertip touch for the projector-camera HCI system[C]//Proc of IEEE International Symposium on Circuits and Systems.[S.l.]:IEEE Press,2014:526-529.
[8]Felzenszwalb P F,Huttenlocher D P.Efficient belief propagation for early vision[J].International Journal of Computer Vision,2004,1(1):41-54.
[9]Hartley R I.In defense of the eight-point algorithm[J].IEEE Trans on Pattern Analysis and Machine Intel igence,1997,19(6):580-593.
[10]Agarwal A,Izadi S,Chandraker M,et al.High precision multi-touch sensing on surfaces using overhead cameras[C]//Proc of IEEE International Workshop on Horizontal Interactive Human-Computer Systems.[S.l.]:IEEE Press,2007:197-200.
[11]Flynn T,Dahlmann-Noor A,Bunce C,et al.Lamp Top:touch detection for a projector-camera system based on shape classification[C]//Proc of ACM International Conference on Interactive Tabletops and Surfaces.New York:ACM Press,2013:429-432.
[12]Harrison C,Tan D,Morris D.Skinput:appropriating the body as input surface[C]//Proc of SIGCHI Conference on Human Factors in Computing Systems.New York:ACM Press,2010:453-462.
[13]Winkler C,Chtefeld M,Dobbelstein D,et al.Surface Phone:a mobile projection device for single and multiuser everywhere tabletop interaction[C]//Proc of SIGCHI Conference on Human Factors in Computing Systems.New York:ACM Press,2014:3513-3522.
[2]Harrison C,Benko H,Wilson A D.Omni Touch:wearable multitouch interaction everywhere[C]//Proc of the 24th Annual ACM Symposium on User Interface Software and Technology.New York:ACM Press,2011:441-450.
[3]Hu Jun,Li Guolin,Xie Xiang,et al.Bare-fingers touch detection by the button’s distortion in a projector-camera system[J].IEEE Trans on Circuits&Systems for Video Technology,2013,24(4):566-575.
[4]Dai J,Chung C K R.Touchscreen Everywhere:on transferring a normal planar surface to a touch-sensitive display[J].IEEE Trans on Cybernetics,2013,44(8):1383-1396.
[5]Park H,Seo B,Park J.Subjective evaluation on visual perceptibility of embedding complementary patterns for nonintrusive projection-based augmented reality[J].IEEE Trans on Circuits&Systems for Video Technology,2010,20(5):687-696.
[6]Song Wei,Xie Xiang,Li Guolin,et al.Flexible method to calibrate projector-camera systems with high accuracy[J].Electronics Letters,2015,50(23):1685-1687.
[7]Cai Xilei,Xie Xiang,Li Guolin,et al.A new method of detecting fingertip touch for the projector-camera HCI system[C]//Proc of IEEE International Symposium on Circuits and Systems.[S.l.]:IEEE Press,2014:526-529.
[8]Felzenszwalb P F,Huttenlocher D P.Efficient belief propagation for early vision[J].International Journal of Computer Vision,2004,1(1):41-54.
[9]Hartley R I.In defense of the eight-point algorithm[J].IEEE Trans on Pattern Analysis and Machine Intel igence,1997,19(6):580-593.
[10]Agarwal A,Izadi S,Chandraker M,et al.High precision multi-touch sensing on surfaces using overhead cameras[C]//Proc of IEEE International Workshop on Horizontal Interactive Human-Computer Systems.[S.l.]:IEEE Press,2007:197-200.
[11]Flynn T,Dahlmann-Noor A,Bunce C,et al.Lamp Top:touch detection for a projector-camera system based on shape classification[C]//Proc of ACM International Conference on Interactive Tabletops and Surfaces.New York:ACM Press,2013:429-432.
[12]Harrison C,Tan D,Morris D.Skinput:appropriating the body as input surface[C]//Proc of SIGCHI Conference on Human Factors in Computing Systems.New York:ACM Press,2010:453-462.
[13]Winkler C,Chtefeld M,Dobbelstein D,et al.Surface Phone:a mobile projection device for single and multiuser everywhere tabletop interaction[C]//Proc of SIGCHI Conference on Human Factors in Computing Systems.New York:ACM Press,2014:3513-3522.