Aiming at the shortcomings of classic human motion comparison and recognition method

the cumbersome installation

large demand for equipment

not strong interaction

high cost

and large amount of data

use OpenPose to improve the accuracy

simplicity and interactivity of the comparison of motion recognition.Use the OpenPose algorithm for data analysis and mining

detect the key point information of the human body in image and calculate the distance

then calculate the included angle

determine the inadequacies of the human body movement and prompt feedback.The experimental results show that the system requires simple equipment installation

reducs demand

enhances interactivity

reduces cost and data quantity

and it has strong robustness to noise interference.