基于Kinect深度信息的手势分割与识别

Gesture Segmentation and Recognition Based on Kinect Depth Data

针对手势识别对环境背景要求高、分割的手势往往包含手腕及手指靠拢易造成误识别等问题,提出了一种基于深度信息的手势识别方法。采集手势深度图;接着利用手生成器获取手心信息分割手势,为了去除多余的手腕信息,增加了手掌近似正方形的约束条件;利用扫描线法获取拇指外其它四指数,并结合相邻手指宽度比例及拇指位置的特殊性实现手势的识别。实验结果表明,该方法的平均识别率达到98.4%,实时性好,且对不同光照和复杂背景具有很好的鲁棒性。

Aiming at the problems that gesture recognition required high environmental background, segmented gesture usually contained wrist data and closing fingers easily caused false recognition, a gesture recognition method based on depth data was proposed. It captured gesture depth map, and it used Hands Generator to obtain the information of palm for gesture segmentation, in order to remove redundant wrist data, the constraint of the palm which looks like a square was added. The number of all the other four fingers except thumb could be acquired with the use of the scanline method, therefore, the width ratio of the adjacent fingers and the peculiarity of the thumb position were integrated to achieve the gesture recognition. Experimental results show that the average recognition rate of the method is 98.4%, and the method has good real-time performance and robustness in the different illumination conditions and complex backgrounds.