Conveyor rubber belt deviation detection method based on edge detection

The invention discloses a conveyor rubber belt deviation detection method based on edge detection. The method comprises the following steps: acquiring a working video stream of a conveyor rubber belt site; intercepting a video frame in the working video stream to obtain an adhesive tape image, and preprocessing the adhesive tape image; based on the preprocessed image, using a preset edge detection algorithm to obtain a binarized image; detecting linear features in the binarized image by using a preset transformation detection algorithm; performing least square fitting on the detected linear features to obtain complete linear feature parameters; and the detected linear characteristic parameters are judged, if the linear characteristic parameters are in an abnormal interval, it is judged that the current conveyor rubber belt has deviated, and at the moment, an alarm is given to prompt that the rubber belt has deviated. According to the technical scheme, the operation condition of the conveyor rubber belt can be