To satisfy the needs of the human-machine interaction during the astronaut extravehicular activity ( EVA) , a target selection scheme for astronauts was proposed based on the hand motion er-gonomic analysis of the EVA spacesuit gloves. The scheme combined with the eye tracker and the hand gesture recognition technology could realize the"hands free" interaction during EVA tasks. An eye tracker was used to determine the target of interest and a camera was used to capture the astro-naut' s hand gesture. Then, a gesture recognition algorithm was developed based on the sparse filte-ring feature extraction and the neural network classifier to realize the interaction function according to the predefined target selection command. The experimental results showed that recognition rate was more than 95％, which can provide a prototype basis for the future integration into the spacesuit.%针对航天员出舱作业(EVA)时的人机交互需求,结合着舱外服手套后手部动作的工效学分析,提出了一种结合眼动仪和手势识别技术的航天员目标选取方案,使航天员真正达到"解放双手"的目的.该方案采用眼动仪获取航天员"感兴趣目标区域"的位置信息,利用摄像头捕获航天员手势动作,并基于稀疏滤波的特征提取方法和神经网络分类器对手势进行识别,根据预定义的目标选取指令实现交互功能.试验结果表明,手势识别算法的识别率可达到95％以上,为后期将该交互系统集成到航天服中提供了原型依据.
展开▼
