【作者】 黄文秀；

【导师】 刘宏；

【作者基本信息】 华中科技大学 ， 计算机应用技术， 2009， 硕士

【摘要】 多点触摸技术是自2007年起兴起的一项多路输入技术,是计算机人机交互领域的一项重要创新。多点触摸技术提供了良好的用户体验,在社会服务领域有着很大的应用潜力,且其相关技术的推广应用甚至正作为一个新兴产业在蓬勃发展,具有明显的商业价值和十分诱人的发展前景。多触摸技术的实现方案之一是基于计算机视觉技术。这种实现方案具有成本低廉、易于扩展的特点,尤其适合于大型的互动场合应用。主要研究工作和创新点如下:介绍了几种常用的多点触摸技术的实现原理,研究与讨论了多点触摸技术实现中的一般理论和技术性问题,并基于计算机视觉技术和红外光学技术实现了一个完整的多点触摸系统。该系统的体系架构可以划分为六个层次。若将系统建立成C/S模型,则系统包含一个通用的输出触摸事件的服务端驱动,和多个支持多点触摸输入的客户端应用程序。介绍了多路触摸信号检测模块各个流程的实现方法,其中提出了一种基于Blob的触摸信息分析方法,使得系统能感应多触摸点的二维坐标和压力信息。讨论了多触摸点运动分析技术。采用了一种将视频帧间的多目标运动跟踪问题归约到帧间触摸点匹配问题的新方法,在该方法的基础上首次提出一种基于二分图最优匹配的方法来解决帧间触摸点的匹配问题。实验证明,该算法能正确地判断多触摸点的运动状态,且能满足实时性的要求。讨论了多触摸技术中的多用户判别技术。采用了一种面向应用对象的多用户判别策略,研究并实现了支持单用户的鼠标模拟技术,及支持多用户的多指移动、双指缩放、双指旋转及压力感应等多触摸手势的识别方法。经过实验验证,提出的相关算法和策略能实现多用户多触摸手势识别功能,且实时性强,交互方式人性化,具有市场推广和应用价值。更多还原

【Abstract】 Multi-touch technology is a multi-channel input technology which has been rising since 2007. It is an important innovation in Human and Computer Interaction (HCI) field. Multi-touch technology provides good user experience, and has great potential to apply on many social service fields. Its related technology has significant commercial potential and attractive development prospect.One of the Multi-touch solutions is based on Computer Vision technology. This solution is low cost, and very easy to expand, and is especially fit for large situation of interaction. Follow is the main research work and innovations:Introduce some technology which are used on multi-touch product now, and discuss the general problems during the implement of a multi-touch system which based on both Computer Vision and infrared optics technology. The system architecture can be divided into six levels, and if build as C/S model, the architecture can be composed of a common driver which outputs the touch events in real time, and some client applications which support the Multi-touch interaction.Introduce the algorithm of each step in the multi-touch signal detection module. Especially, propose a Blob based method to analyze the touch information, which enables the system be sensitive to both position and pressure of touch.Discuss the motion analysis problem of touch points. Apply an idea that the motion analysis problem can be transformed into a match problem between consecutive frames. According to this idea, propose a new method based on Optimal Matching of Bipartite Graph Algorithm to solve the match problem. The experiment proves that the new methods could correctly judge the motion status of touch points, and can run in real time.Discuss the multi-user support technology in Multi-touch system, and propose a strategy based on different application object to distinguish multi-user. Show some Multi-touch applications, such as cursor simulation, and multi fingers to move, zoom and rotate something, also show an application which is pressure sensitive.The experiments show that the algorithms and strategies discussed in this paper can support Multi-touch technology well, and useful for many relative applications.更多还原