Steel plate corner detection method and system under complex background

Abstract

The invention discloses a steel plate corner detection method and system under a complex background. The method comprises the following steps: 1, obtaining a steel plate image and extracting mark points in the image; 2, correcting the image; 3, extracting a region of interest; 4, carrying out edge detection; 5, sampling and fitting the four edges of the steel plate respectively; and 6, judging a detection result. The existing angular point detection method has the problems of poor reliability and robustness and high calculation complexity under the conditions that the edge contour of a steel plate is discontinuous and irregular, the vertex is incomplete and the noise interference is more. The method provided by the invention solves the problems, and is high in reliability, strong in robustness, low in computer operational capability requirement, and very suitable for completing a corner detection task in an industrial scene of steel plate processing.

Description

technical field [0001] The invention relates to image processing technology, in particular to a steel plate corner detection method and system under complex background. Background technique [0002] The steel industry is one of the important pillar industries in the contemporary industrial field. With the rapid development of my country's economy, steel production has accounted for 50% of the world. As an important product form of the steel industry, steel plates are widely used industrial materials in contemporary society, and are widely used in the construction industry, automobile manufacturing industry, shipbuilding industry, and aircraft manufacturing industry, etc. The development of the steel industry has also strongly promoted the development of other industries and fields. Even since the first industrial revolution, the development level of the steel industry has been used as one of the standards to measure a country's industrial development level and economic devel...

AI Technical Summary

Problems solved by technology

However, although traditional methods have certain advantages in industrial scenes, they often perform poorly when dealing with images with complex backgrounds.

For example, the method proposed by CN108898148B detects the corners of the steel plate. If the outline detected by the edge detection of the steel plate is not closed, the apex is incomplete or the outline of other objects in the background interferes a lot, it is difficult to accurately locate the four vertices of the steel plate

Another example is that the method proposed by CN106936964A is also difficult to perform the task of steel plate corner detection, because the edge of the steel plate is uneven, the lines of the steel plate outline in the edge detection result are messy and interlaced, and the effect of Hough transform is not ideal

In summary, there are still obvious deficiencies in the steel plate corner detection method under complex backgrounds.

The complex background includes three meanings: 1. The contrast between the background and the steel plate is low, and the edge of the steel plate is not clear; 2. There are many noises and interfering objects in the background; 3. The lighting in the environment is complex and changeable

Images