Monocular hand gesture recognition systems usually model a human hand as a pixel or a blob by which the motion of the whole hand are analyzed and the appearance features are extracted.

单目视觉的手势识别系统，通常把人手建模成一个像素或者一块，从整体上分析手势的运动参数并提取表观特征。

youdao

Most gesture recognition systems use skin color model to segment hand. The segmentation results are affected by to the light, background and other conditions.

目前手势识别系统主要是利用肤色模型分割手部区域，检测结果易受光照、背景等条件影响。

youdao

That opens up the possibility of putting virtual objects into the real world, letting you "pick up" a computer-generated 3D architectural model and spin it around in your hand, for instance, or gesture to control a virtual display appearing on an actual wall.

ENGADGET