Bamboo cane surface defect detection method based on triple loss network

Abstract

The invention relates to a bamboo cane surface defect detection method based on a triple loss network. The method comprises the following steps: S1, collecting bamboo cane surface defect data througha camera mounted on a bamboo cane sorting robot to form a bamboo cane surface defect data set; S2, performing triple loss network training on the images in the bamboo cane surface defect data set to obtain an anchor point prediction matrix, a size prediction matrix and a thermodynamic diagram prediction matrix; S3, calculating anchor point prediction matrix loss, size prediction matrix loss and thermodynamic diagram prediction matrix loss to obtain total loss of triple loss network updating; S4, continuously updating and optimizing to obtain an optimal convolution weight parameter and an optimal offset parameter based on the updated total loss of the triple loss network calculated in the step S3; and S5, obtaining an anchor point prediction matrix and a size prediction matrix by updating the triple loss network of the convolution weight parameter and the offset parameter of the test image in the bamboo cane surface defect data set, and then obtaining the category and the size of the detected target defect.

Description

technical field [0001] The invention belongs to the field of defect detection, and in particular relates to a method for detecting defects on the surface of bamboo strips based on a triple loss network. Background technique [0002] Bamboo occupies a very important position in the world's forest resources and is known as the "second forest". China is the largest bamboo-producing country in the world, and the bamboo industry is also an important part of my country's forestry industry, playing an irreplaceable role in my country's economic and social development. Bamboo slabs are the first step in the molding of most handicrafts, which are spliced ​​by bamboo strips after bamboo fragments, drying, carbonization and other processes. Usually, before splicing, the bamboo strips need to be inspected for defects, and then spliced ​​into bamboo slabs of different qualities according to different defects and the severity of the defects. However, the factory needs to consume a lot o...

AI Technical Summary

Problems solved by technology

If the second-order target detection algorithm is used in the detection of this defect, because this type of algorithm takes a long time, it cannot achieve the effect of real-time detection

If a first-order target detection algorithm is used, since the backbone network of this type of algorithm is not tailored for bamboo defects, it will lead to problems such as insufficient detection accuracy

Images