A motion-capture-based action guidance method and device

Abstract

The invention discloses an action guidance method based on motion capture, which includes: acquiring standard action images and user action images; outputting digital signals of key points and two-dimensional coordinates of human bodies in the standard action images and user action images; recognizing human body limbs The length and the included angle of limbs identify the digital signals of each joint point of the human body and the two-dimensional coordinates of each joint point in the standard action image and the adjusted user action image; the two-dimensional coordinates of each key point of the human body in the standard action image are respectively The digital signal corresponds to the first human skeleton model, and the adjusted digital signal of the two-dimensional coordinates of each key point of the human body in the user action image corresponds to the second human skeleton model; compare the actions of the first skeleton model with the actions of the second skeleton model The included angle between the limbs is used to judge whether the user's action is within the error range from the standard action; if the deviation between the user's action and the standard action exceeds the threshold, the user is reminded to adjust the action in the direction of reducing the error.

Description

technical field [0001] The present invention relates to the field of human-computer interaction technology, in particular to a method and device for motion guidance based on motion capture. Background technique [0002] With the development of the economy and the progress of the society, people have higher and higher requirements for the quality of life, and pay more attention to enriching their entertainment life and improving their physical fitness through yoga, dance, fitness equipment, etc. However, due to the high cost of study classes and the unwillingness to express themselves in front of others, many people need action guidance systems to improve their learning efficiency. [0003] Regarding the motion capture technology, the existing relatively mature technologies can be divided into mechanical, acoustic, electromagnetic, inertial navigation and optical. Compared with other forms, the advantage of the optical type is that the supporting peripherals are simple, and ...

AI Technical Summary

Problems solved by technology

Furthermore, the processing flow and time complexity of the guidance system are relatively cumbersome

[0005] It can be seen that for general users, it is difficult to meet the high material conditions of more than six cameras and the limitation of large venues.

It is very cumbersome to change monochromatic clothing and wear light spots before use

The cumbersome processing flow and processing time complexity lead to insufficient action matching and recognition

Images