Foreign matter deviation detection method, foreign matter deviation detection device and foreign matter deviation detection system

The invention provides a foreign matter deviation detection method, a foreign matter deviation detection device and a foreign matter deviation detection system. The method comprises the following steps: acquiring a plurality of original images; training the plurality of original images by using a deep convolutional neural network to obtain an image detection model; acquiring a current image of the surface of the conveying belt in real time, inputting the current image into the image detection model, and outputting target detection frame information corresponding to an object in the current image; detecting a target position of the article according to the target detection frame information; and under the condition that the distance between the target position and the center line of the conveying belt is larger than the preset distance, alarm information is controlled to be sent out. The method solves the problems that in the prior art, a conveyor is limited by the influence of the working environment, inspect