在非特定人自然的人体动作识别中，基元特征能够大大降低参数的离散度，提高系统抗噪声能力、鲁棒性和识别率。
Primitives can reduce the scatter of the motion parameters greatly and improve the subject-independent action recognition rate and robustness.
为解决现有虚拟训练软件的人体动作输入设备沉浸感和训练效果不足的问题，采用DSP和微机电系统(MEMS)构建人体动作识别系统。
To improve the sense of immersion and training effects of human detection input device for the virtual training software, the system of human motion detection based on DSP and MEMS was designed.
本作品是一个以EC5主板为平台构建的多功能智能舞蹈机器人DDX-08。它具备单目视觉能力，通过人脸识别算法和跟踪算法，实现了人体动作的识别和跟踪。
DDX-08 is a multi-purpose intelligence dancing robot based on EC5-1719CLDNA, which can identify and track human motion through monocular machine vision and tracking algorithm under complex background.
应用推荐