单人人体关键点检测模型在落地时有其他人或无人时，出现误判，如何解决？

单人人体关键点检测模型在落地时有其他人或无人时，出现人员关键点误判，如何解决？

模型采用movenet

改用多人
或使用CV的办法判断非单人

正常

不知道这个对你说是否有帮助：

Human Falling Recognition Based on Movement Energy Expenditure Feature,Discrete Dynamics in Nature and Society - X-MOL Falls in the elderly are a common phenomenon in daily life, which causes serious injuries and even death. Human activity recognition methods with wearable sensor signals as input have been proposed to improve the accuracy and automation of daily falling recognition. In order not to affect the normal life behavior of the elderly, to make full use of the functions provided by the smartphone, to reduce the inconvenience caused by wearing sensor devices, and to reduce the cost of monitoring systems, https://www.x-mol.com/paper/1459646041528631296?adv

可以参考这个

MoveNet-谷歌轻量级人体姿态估计算法 - 知乎 MoveNetGoogle提供的在线演示： https://storage.googleapis.com/tfjs-models/demos/pose-detection/index.html?model=movenetMoveNet 是一个 Bottom-up estimation model， 使用heatmap。 网络架构主要分为三个部… https://zhuanlan.zhihu.com/p/466887506