Gesture recognition device, gesture recognition method and virtual reality system

Abstract

The invention provides a gesture recognition device, a gesture recognition method and a virtual reality system. The gesture recognition device includes: an imaging device, used to take images of the hand; a first inertial sensor, configured to be fixed relative to the imaging device, and used to sense the lens orientation information of the imaging device; a second inertial sensor, arranged on the hand , for sensing the orientation information of the palm of the hand; the processor, connected to the first inertial sensor and the second inertial sensor, is used to determine the relative direction of the palm of the hand relative to the imaging device according to the orientation information of the lens and the orientation information of the palm of the hand relation. The gesture recognition method includes: determining the lens orientation information of the imaging device; determining the palm orientation information; and determining the relative direction relationship between the palm of the hand and the imaging device according to the lens orientation information and the palm orientation information. Virtual reality systems include gesture recognition devices as well as head-mounted devices. Thereby, gesture recognition can be made more accurate.

Description

technical field [0001] The invention relates to a gesture recognition device, a gesture recognition method and a virtual reality system. Background technique [0002] With the rapid development of technologies related to virtual reality, human-computer interaction, and image recognition, there is an increasing demand for accurate gesture recognition in various industries. It can be applied to: smart home control, vehicle operation control, PC and mobile terminal control, industrial design and other aspects. And its commercial value is also increasing day by day. [0003] There are also various methods of gesture recognition, which can be roughly divided into three technologies: image recognition technology based on light technology, motion capture technology based on inertial sensors, and hand shape simulation technology based on mechanical structure. These three technologies have their own advantages and disadvantages and are incompatible with each other. [0004] The te...

AI Technical Summary

Problems solved by technology

Its disadvantages are: it is difficult to judge the front and back of the hand, and it is easy to make a misjudgment; it is greatly affected by light, including outdoor visible light, the laser emitted by the laser camera itself, and the recognition interference of the capture camera itself; the recognition range is limited and limited by the optical path. The tolerance of obstacles is low, and the recognition and judgment of overlapping hands are wrong

However, in the field of gesture recognition, it has some obvious defects: it cannot restore the fine movements of the hand joints; it cannot perform absolute positioning in space, and the integral calculation is performed through the posture information of each part of the body, and the obtained spatial position information causes different degrees of integral drift.

Unable to accurately locate hand movements; easily affected by the ferromagnet in the surrounding environment and reduce accuracy

Images