Flap valve state recognition method and system based on machine vision

The invention belongs to the technical field of image processing, and particularly relates to a flap valve state recognition method and system based on machine vision. The method comprises the following steps: obtaining a flap valve monitoring image in real time, and generating a valve handle mask image set based on a trained valve handle segmentation model; on the basis of the valve handle mask image set, calculating the opening and closing angle of the flap valve handle of the current frame in combination with a centroid method; and counting opening and closing angle changes of the valve handle in continuous time periods, and judging whether the state of the flap valve is abnormal or not. Through intelligent analysis of the monitoring image, the angle change of the valve handle of the flap valve can be monitored around the clock, so that the abnormal state of the flap valve is positioned, and an alarm is given. The problems of high manual inspection cost and low efficiency of the existing flap valve are sol