面向三维场景造型的徒手手势交互方法

An Approach to Free-Hand Interaction for 3D Scene Modeling

针对手势交互在场景造型应用中的问题,从3个层面分析并提出解决思路,意图建立一种面向三维场景造型的徒手手势交互方法.首先,在宏观上基于用户活动和系统任务,构造面向场景造型的手势交互框架;其次,在中观上提出完整实用的手势集构造方法,并用此方法为本文系统设计手势集;再次,在微观上针对场景造型中手势识别的"米达斯"接触问题,从时间、空间、手势辅助3方面提出优化方法;最后,通过实验验证了所提出方法的可用性并总结了未来的研究方向.

To solve the problem of a free-hand interaction method in 3 D scene modeling, some possible solutions were put forward from three levels for the key problems of scene modeling. On the macroscopic level, an interaction frame was established based on user activities and system tasks. On the middle level, a method was proposed to construct a complete and practical gesture set, and then a gesture set was designed for the system based on the proposed method. On the microcosmic level, to solve the 'Midas touch' problem, an optimal method was put forward from the aspects of time, space, and gesture assistance to improve the recognition rate of gestures. Finally, experiment was carried out to verify the availability of proposed methods, providing a future research direction.