面向投影环境的计算机视觉交互信息获取

Interaction Information Acquisition for Projection Environment Based on Computer Vision

针对面向投影环境的视觉交互信息获取问题,提出了一种基于前景检测和立体视觉的体感交互信息获取方法。该方法使用双摄像头实时完成投影环境下的人体前景检测、姿势识别以及三维空间定位,能够为人机交互提供人体位置信息、姿势信息。为了验证该方法的有效性,设计并实现了一套虚拟场景视点控制系统。实验证明,该方法能够满足用户与虚拟场景实时交互的需要。

To get the visual interaction information in projection environment, a method of getting somatosensory interaction information based on foreground detection and stereo vision is proposed. In this approach, two cameras are used for human body detection, gesture recognition and location in three-dimensional space. So the position and gesture information can be obtained for human-computer interaction. At last, a virtual scene viewpoint control system is designed and implemented to verify the feasibility of the method. The experimental results show that this method can meet the needs of real-time interaction.