Steel bar intelligent identification and counting method and system

Abstract

The invention discloses a steel bar intelligent identification and counting method and system, and the method comprises the steps of collecting a picture data set with a steel bar cluster cross section image, and obtaining a training sample set based on the collected picture data set; establishing a deep convolutional neural network model, and training the deep convolutional neural network model based on the training sample set data; inputting the to-be-identified picture into the trained deep convolutional neural network model to obtain a preliminary output result of the deep convolutional neural network model; processing the score map of the preliminary output result by using a non-maximum suppression algorithm, converting the score of each region into a point, and removing the mistakenly identified steel bars in the preliminary output result by using an outlier deletion algorithm to obtain a final output result of the deep convolutional neural network model; based on the final output result of the deep convolutional neural network model, obtaining the number and positions of the steel bars in the to-be-identified picture. The method can efficiently, accurately and intelligentlyidentify the steel bars and count the steel bars.

Description

technical field [0001] The invention relates to the field of intelligent processing of steel bars, in particular to a method and system for intelligent identification and counting of steel bars. Background technique [0002] Steel has been widely used in many aspects of real life and is closely related to people's lives. As the basic finished product produced by iron and steel enterprises, steel bars are widely used in many industries, especially the construction industry. Most steel bar manufacturers use tons as the unit of measurement to produce and sell by weight. However, in practical applications, it is often not the total weight of steel bars that is mastered, but the number of steel bars. At present, manual counting is generally used on construction sites. This method is simple, but The work intensity is high, while the work efficiency is low and the cost is high. Therefore, realizing accurate automatic counting of bundled steel bars can not only make workers' work ...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for intelligent identification and counting of steel bars aimed at the frontal images of steel bars taken in real and complex scenes, aiming to solve the problems of high cost and low efficiency of manual counting of steel bars at present, and the inability to be applied to actual production by using traditional graphic image methods problem, realize the application of deep learning to the field of intelligent identification and counting of steel bars

Images