A gesture recognition device, system and gesture recognition method

Abstract

The invention provides a gesture identification apparatus, system and method. The method comprises the steps of obtaining six-axis pose data of each finger through a six-axis inertial sensor of each finger module; obtaining nine-axis pose data of a palm and nine-axis pose data of an arm through a first nine-axis inertial sensor of a palm module and a second nine-axis inertial sensor of an arm module; and sending the six-axis pose data of each finger, the nine-axis pose data of the palm and the nine-axis pose data of the arm to an upper computer. The upper computer processes the six-axis pose data of each finger and the nine-axis pose data of the palm to obtain relative pose data of each finger and the palm, and processes the nine-axis pose data of the palm and the nine-axis pose data of the arm to obtain a spatial position of the palm. According to the gesture identification apparatus, system and method, 6DOF tracking is realized, so that the gesture identification rate is increased.

Description

Technical field[0001]The present invention relates to the field of action recognition, and more specifically, to a gesture recognition device, system and gesture recognition method.Background technique[0002]Virtual reality technology (English full name: Virtual Reality, English abbreviation: VR) is an important direction of simulation technology, which is a collection of simulation technology and computer graphics man-machine interface technology, multimedia technology, sensor technology, network technology, etc. , Is a challenging cross-technology frontier subject and research field. Virtual reality technology mainly includes aspects such as simulated environment, perception, natural skills and sensing equipment. The simulation environment is a real-time dynamic three-dimensional realistic image generated by a computer. Perception means that the ideal VR should have the perception that all people have. In addition to the visual perception generated by computer graphics technology, ...

AI Technical Summary

Problems solved by technology

For example, air mouse handles are generally difficult to achieve 6DOF (English full name: Sixdegrees of freedom) tracking, and cannot recognize gestures; optical gesture recognition controllers have high computational complexity, high power consumption and cost, and are easily interfered by light intensity. The generalization ability in the recognition rate is limited; glove controllers generally use various pressure sensors to detect joint displacement, and it is difficult to achieve 6DOF tracking

[0004] To sum up, the gesture recognition rate of the current VR controller is low, and the user experience is poor.

Images