Escalator monitoring video anomaly detection method and system

The invention discloses an escalator monitoring video anomaly detection method and system, and relates to the field of escalator detection, and the method comprises the steps: obtaining a key point heat map corresponding to each frame of picture in a data set through a combined trained YOLOv5 target detection model and an HR-Net key point extraction model, and obtaining a key point inter-frame change map corresponding to the key point heat map; a convolutional neural network model is obtained by training a convolutional neural network through an image label pair including a key point inter-frame change graph and a corresponding label, and when detection is started, a to-be-detected escalator monitoring video picture set is input into a YOLOv5 target detection model frame by frame to obtain a pedestrian target frame position corresponding to each frame of picture. According to the method, pedestrian target frame positions are obtained, key point heat maps corresponding to the pedestrian target frame positions