Bar on-line automatic counting method based on modified gradient Hough circle transformation

Abstract

The invention relates to a bar on-line automatic counting method based on modified gradient Hough circle transformation. The method includes that after threshold parameters of normal radii, minimum radii, maximum radii and combined radii of bars in various specifications are determined, each frame of real-timely collected bar end surface patterns is processed by the following steps of firstly, reinforcing a current frame of bar end surface patterns on the basis of a modified gradient Hough circle transformation method, subjecting the current frame of bar end surface patterns to Regional Max detection and distance detection according to the corresponding threshold parameters, determining an actual observation central point of a current frame of bar end surfaces, and finally, establishing a relevance matching pair relationship between the actual observation central point of the current frame of bar end surfaces and an actual observation central point of a prior frame of bar end surfaces according to horizontal motion speeds of the bars, wherein in each relevance matching pair relationship, if the actual observation central point of the current frame and the actual observation central point of the prior frame are distributed on the left side and the right side of a bar counting central datum line respectively, a counting variable is added by one, and otherwise, the counting variable is reduced by one. The bar on-line automatic counting method has the advantages of being high in real-time performance, high in counting accuracy and capable of bidirectional counting.

Description

technical field [0001] The invention belongs to the technical field of on-line automatic counting of bars. In particular, it relates to an online automatic bar counting method based on improved gradient Hough circle transformation. Background technique [0002] The production of bar products in rolling mills requires that the finished products be packaged in standardized bundles according to the specified number of counts. However, at present, the bars produced in my country's rolling mills are manually counted, which is not only prone to errors, low efficiency, and the packaging quantity cannot meet the requirements, but also does not match with automatic rolling, which affects the improvement of production efficiency and equipment level; on the other hand, due to packaging The exact number of counts cannot be guaranteed, and the market sales are only measured by weight, and the due economic benefits cannot be obtained from the negative tolerance rolling method popular in t...

AI Technical Summary

Problems solved by technology

Photoelectric technology is suitable for the situation where there is no overlapping or crossing of the rods or the overlapping is not serious. As the diameter of the rod decreases, the situation of overlapping and crossing becomes more and more serious. At this time, it is difficult to solve the automatic counting problem only with photoelectric technology

The use of digital image processing technology can better solve the identification and counting of bars in the case of overlapping and crossing, but the image processing technology is limited by background noise, light influence and processing methods, and the existing online automatic bar counting method is not fully applicable In various bar production sites

Images