AI scrap steel unloading state detection method based on machine vision

Abstract

The invention relates to the field of metallurgy and the field of image recognition, in particular to an AI scrap steel unloading state detection method based on machine vision, and the method comprises the steps: obtaining image frame data through image collection equipment; preprocessing data with steel scraps in a video stream of the image frame, and dividing the data according to a proportion to form a data set; obtaining a trained detection model; inputting video stream image frame data into the trained detection model, and returning the category of the video stream image frame data and the coordinates of the detection frame; and an output result of the trained detection model is sent to an unloading state analysis system, and a current unloading event state is given through the unloading state analysis system. The device has the advantages that the functions of automatically positioning the discharging position of the suction cup and the like are achieved; the improved network model is based on a yov5 network, so that the positioning accuracy and the recognition accuracy are improved, the labor intensity of staff is reduced, the inspection and unloading speed is improved, the intelligence, precision and high efficiency of the scrap steel unloading process are achieved, and the reliability is high.

Images