Elevator door anomaly detection method based on video image analysis

The invention relates to the field of image data processing, in particular to an elevator door anomaly detection method based on video image analysis, which comprises the following steps: carrying out initial linear region identification on an elevator door gray level image, confirming an initial linear region which is composed of a plurality of linear units, and then according to the straightness corresponding to the plurality of linear units, determining the initial linear region; calculating the confusion degree of the initial linear region, marking the initial linear region as a final linear region when the confusion degree of the initial linear region is greater than a preset threshold value, and calculating the threshold value parameter of the anomaly detection model based on the region angle between the final linear regions; and finally, inputting the gray level image of the elevator door into an anomaly detection model corresponding to the threshold parameter, and confirming the working state of the e