对人体动态行为的准确分析对于克服运动多样性和行为适应性的局限性非常重要。在本文中,提出了一种基于可穿戴设备的人体动态行为识别方法。该方法通过六轴传感器收集加速度和角速度数据,以识别包含时间序列中特定行为特征的信息。人体运动数据采集平台,DMP姿态求解算法,并采用阈值算法进行处理。在这个实验中,十名志愿者在他们的双侧前臂上佩戴了可穿戴传感器,上臂,大腿,小牛,和腰部,和站立的运动数据,走路,在学校走廊和实验室环境中对跳跃进行了采集,以验证这种可穿戴人体运动识别方法的有效性。结果表明,站立的识别准确率较高,走路,跳跃达到98.33%,96.67%,94.60%,分别,平均识别率为96.53%。与同类方法相比,该方法不仅提高了识别精度,而且简化了识别算法,有效节省了计算资源。该研究有望为人体动态行为识别提供新的视角,促进可穿戴技术在日常生活辅助和健康管理领域的广泛应用。
The accurate analysis of human dynamic behavior is very important for overcoming the limitations of movement diversity and behavioral adaptability. In this paper, a wearable device-based human dynamic behavior recognition method is proposed. The method collects acceleration and angular velocity data through a six-axis sensor to identify information containing specific behavior characteristics in a time series. A human movement data acquisition platform, the DMP attitude solution algorithm, and the threshold algorithm are used for processing. In this experiment, ten volunteers wore wearable
sensors on their bilateral forearms, upper arms, thighs, calves, and waist, and movement data for standing, walking, and jumping were collected in school corridors and laboratory environments to verify the effectiveness of this wearable human movement recognition method. The results show that the recognition accuracy for standing, walking, and jumping reaches 98.33%, 96.67%, and 94.60%, respectively, and the average recognition rate is 96.53%. Compared with similar methods, this method not only improves the recognition accuracy but also simplifies the recognition algorithm and effectively saves computing resources. This research is expected to provide a new perspective for the recognition of human dynamic behavior and promote the wider application of wearable technology in the field of daily living assistance and health management.