Research On Walking Beam Monitoring System Based On Image Recognition

Nowadays,walking beam reheating furnace is widely used in hot rolling.So once walking beam reheating breaks down,it will affect the whole production directly and make money loss.But it is impractical for workers to accurately and timely assess the position of slab in walking beam reheating furnace by monitoring video.Hence research on walking beam monitoring system based on image recognition is proposed and image,displaying the operation of slab,is captured by digital video recorder.The purpose of the thesis is to monitor the walking beam reheating furnace with regular and avoid accident occurred.The main research contents of this thesis are as follows.(1)The characteristics of noises in captured pictures is analyzed.And image de-noising based on product of direction and scale is introduced in this thesis.Then evaluation criteria based on edge detection which evaluates the quality of image de-noising is proposed,according to requirements of captured pictures in the thesis.(2)With changes in position between slab and background in image,gray of edge is changed.So it is unsuitable to detect edge by the same threshold.Therefore,in order to improve image contrast between slab edge and background,image enhancement based on wavelet transform is adopted.Then,the slab edge is detected by Canny operator.After that using Hough transform extract complete,smooth edges of slab.(3)In image,the size of slab is known.Taking advantage of reconstructed image,the relationship of pixel and actual size is assured.At last we can calculate the real distance of the slab in reheating furnace.Simulation results illustrate that using image de-noising based on product of direction&scale not only remove noises but preserve edges.After image enhancement based on wavelet transform,the edges of all the images can be extracted.Eventually,in reheating furnace the real distance of the slab can be monitoring with regular.