基于加锁机制的静态手势识别方法

基于RGB-D（RGB-Depth）的静态手势识别的速度高于其动态手势识别，但是存在冗余手势和重复手势而导致识别准确性不高的问题。针对该问题，提出了一种基于加锁机制的静态手势识别方法来识别运动中的手势。首先，将通过Kinect设备获取RGB数据流和Depth数据流融合成人体骨骼数据流；然后，在静态手势方法中引入加锁机制，并与之前建立好的骨骼点特征模型手势库进行比对计算；最后，设计一款“程序员进阶之路”益智类网页游戏进行应用与实验。实验验证在6种不同运动手势情况下，该方法与纯静态手势识别方法相比，平均识别准确率提高了14.4%；与动态手势识别相比，识别速度提高了14%。实验结果表明，提出的基于加锁机制的静态手势识别方法，既保留了静态识别的速率，实现了实时识别；又能很好地剔除冗余手势和重复手势，提高了识别正确性。

Static gesture recognition method based on locking mechanism

The static gesture recognition speed is higher than that of dynamic gesture recognition for RGB-D (RGB-Depth) data, but redundancy gestures and repeated gestures lead to low recognition accuracy. In order to solve the problem, a static gesture recognition method based on locking mechanism was proposed. First, RGB data flow and the Depth data stream were obtained through Kinect equipment, then two kinds of data flow were integrated into human body skeleton data flow. Second, the locking mechanism was used to identify static gestures, and comparison and calculation were done with the established bone point feature model gesture library before. Finally, an "advanced programmers road" brain-training Web game was designed for application and experiment. In the experiments of six different movement gestures, compared with the static gesture recognition method, the average recognition accuracy of the proposed method was increased by 14.4%; compared with the dynamic gesture recognition method, the gesture recognition speed of the proposed method was improved by 14%. The experimental results show that the proposed method keeps the high speed of static recognition method, realizes the real-time recognition; and also improves the identification accuracy through eliminating redundant repeated gestures.