Person falling detection method and device and electronic equipment

The invention provides a person falling detection method and device and electronic equipment, and the method comprises the following steps: obtaining a monitoring video image; inputting the monitoring video image into a pre-trained neural network to obtain human body key position features and human body motion features in the monitoring video image; and fusing the human body key position features and the human body motion features, classifying the fused features, and judging whether tumble occurs or not. By implementing the method, classification is performed according to the features fusing the human body key position features and the human body motion features, human body behaviors with human body postures similar to falling postures but different motion features can be eliminated, and the accuracy of falling detection is improved. 本发明提供一种人员摔倒检测方法、装置及电子设备，其中，方法如下步骤：获取监控视频图像；将所述监控视频图像输入至预先训练好的神经网络，得到监控视频图像中的人体关键位置特征以及人体运动特征；将所述人体关键位置特征和所述人体运动特征进行融合，将融合后的特征进行分类，判断是否发生摔倒。通过实施本方法，根据融合人体关键位置特征和人体运动特征的特征进行分类，能够排除