Steel tube counting method by combining support vector machine threshold statistics and spot detection

Abstract

The invention provides a steel tube counting method by combining support vector machine threshold statistics and spot detection. The method comprises: stacking cross section two-dimensional images of to-be-identified steel tubes are processed into stacking cross section grayscale images; the grayscale images are classified by using an SVM algorithm, threshold statistics is carried out on a roundness feature parameter and an area feature parameter of a target subarea, and then a roundness threshold range and an area threshold area are generated based on threshold statistic results; and identification of similar circular spots in the stacking cross section grayscale images is carried out by using a spot detection algorithm, identification results are screened by using the roundness threshold range and an area threshold range, and then statistics of the number of spots in the screened spot set is carried out and thus a target steel tube number is obtained. According to the invention, the method has the excellent anti-interference performance and high robustness; the image shooting requirement is low; and for image identification of lots of steel tube targets, excellent performances are presented with low algorithm complexity. The method is suitable for embedded mobile equipment to realize real-time counting.

Description

technical field [0001] The invention relates to a steel pipe counting method, in particular to a steel pipe counting method combining support vector machine threshold statistics and spot detection. Background technique [0002] The construction industry and the steel pipe leasing industry currently mainly use manual counting methods to count steel pipes. The scale of stacked steel pipes usually ranges from 500 to 1500. The entire manual counting process is time-consuming, inefficient, and labor-intensive. The study is used in steel pipe manufacturers and steel pipe leasing manufacturers, and the automatic identification method of steel pipes by taking pictures can reduce the labor intensity of counting workers and improve counting efficiency. [0003] Among the existing automatic counting methods for steel pipes based on image recognition, the circle detection algorithm based on the improved Hough transform and the image segmentation algorithm combined with contour extracti...

AI Technical Summary

Problems solved by technology

However, under complex lighting conditions, this method cannot distinguish between the shadow of steel pipes and the gap between stacks; and as the number of steel pipes to be identified in the picture increases, the number of effective pixels contained in a single steel pipe decreases, resulting in a gap between the complex background and the target to be identified. The difference of contour features is reduced, and the screening threshold for sub-regions becomes difficult, which eventually leads to a rapid decline in recognition accuracy

[0004] Through the research on the problems and solutions of the above algorithms, combined with the actual needs of engineering applications, it is necessary to study the calculation results to be more accurate, and at the same time, the complexity of the algorithm implementation is not too high to meet the needs of industrial applications. New counting method

Images