【摘要】 随着在线健身资源的日益丰富,自主健身已成为新的运动趋势。然而由于缺少专业健身教练的动作指导与纠正,自主健身通常无法保障健身效果且容易造成运动损伤,因此需要对健身动作准确性进行实时监测。现有的健身监测设备往往依托大屏幕、深度摄像头或传感器等硬件,存在设备昂贵、安装不便、使用场景受限等问题,较难满足大众健身的需求。随着人体关键点检测技术的不断成熟,通过手机单目摄像头即可实现对人体姿态的识别,且有较高的准确度和速度,使得在手机端实现低成本、多场景的健身监测成为可能。基于以上背景,设计了三维场景下基于角度阈值的健身动作评估算法,依托于手机单目摄像头和3D人体关键点检测技术,实时检测用户健身动作是否标准并通过语音给出相应提示。同时,在安卓手机上实现了原型系统,通过一系列用户实验验证了系统的可用性与实时性,通过与近年相关工作的对比实验,验证了动作评估方法的准确性。结果表明,本文方法与系统被用户所认可,健身动作评估准确率较高、响应速度满足实时性要求。更多还原

【Abstract】 With the increasing richness of online fitness resources, autonomous fitness has become a new sporting trend.However, due to the lack of action guidance and correction by professional fitness coaches, autonomous fitness usually cannot guarantee the fitness effect and is easy to cause sports injuries, so real-time monitoring of fitness actions is required. Existing fitness monitoring equipment usually relies on professional hardware such as big screens, stereo camera and other sensors. As a result, they fail to satisfy common needs for virtual fitness due to high cost, complexity of installation and limited application scenario. With gradual maturing of human pose estimation technique,identification of human face and movements of limbs can be realized through easily accessible cell phone camera with high accuracy and speed. Low cost, multi-scenario virtual fitness monitoring on mobile terminal thus it made possible.Based on the background above, this work designs a fitness action evaluation algorithm based on angle thresholds in 3D scenes which relies on cell phone monocular camera and 3D human key point detection technology. The algorithm can detect whether the user’s fitness actions are standard in real time and give corresponding responses through voice. The work has implemented a prototype system on an Android phone. This work verifies the usability and real-time performance of the algorithm and the system through a series of user experiments. It also verifies the accuracy of the action evaluation algorithm through comparative experiments with relevant work in recent years. Results shows that the algorithm and functions of the prototype system were greatly recognized by the users with high accuracy, reasonable responding speed for real time usage.更多还原