Research on human posture recognition system based on inertial sensor
Han Chenghao, Mao Jiayi, Yongyong Yang · 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · 2022
Aiming at the problem of high complexity of human motion and serious occlusion by video acquisition, a human posture recognition system based on mpu9250 inertial sensor and CC2530 is designed in this paper. Using the gyroscope, accelerometer and magnetometer inside the sensor, the acceleration, angular velocity and angle of three axes can be calculated, and then the attitude angle can be calculated. Through the combination of ZigBee network and esp8266, the collected data can be sent to the upper computer wirelessly. In this paper, through the research of human bones, the human model is established by using Makehuman software, and the generated FBX human model file is imported into unity3d to drive the human model. Finally, the purpose of real-time display of human motion posture is achieved