Optimizing Human Motion Posture Detection and Humanized Computing for Smart Health Applications
Weiwei Wang, Jingshan Zhang · 2025
Existing human motion detection technologies have problems such as insufficient accuracy and poor real-time performance, which makes it difficult to meet the needs of health management. This paper proposes a human motion posture detection and humanized calculation method based on multi-sensor fusion and LSTM. This paper first deploys IMU sensors at key parts of the human body, and uses visual sensors to capture the three-dimensional posture information of human motion, and obtains physiological data such as heart rate and number of steps through wearable devices such as smart bracelets. Secondly, the IMU data is denoised and calibrated to eliminate sensor errors. Next, the fused data is trained using a long short-term memory network (LSTM). The rationality of the motion posture is then analyzed, and the user's exercise intensity and health status are evaluated based on the motion data and physiological data. In terms of posture recognition accuracy, the average value of this method is 92.61 %. In terms of abnormal posture detection rate, the detection rate of some data points of this method is close to 100%. At the same time, the maximum recognition time of this method is only 789 milliseconds, and the minimum recognition time is as low as 503 milliseconds, which is better than the traditional method. The optimized human motion posture detection and humanized calculation method proposed in this paper realizes high-precision detection of human motion and intelligent health management through multi-source data fusion, LSTM construction, human kinematics analysis and personalized health assessment.