Unlock instant, AI-driven research and patent intelligence for your innovation.

Filter bag mouth position detection method based on depth separable convolution YOLOv4 model

A detection method and filter bag technology, applied in the field of computer vision, can solve the problems of factory production requirements, unsatisfactory detection accuracy, inaccurate product position positioning, etc., to reduce the amount of parameters, increase the calculation speed, and reduce the total amount of parameters. Effect

Pending Publication Date: 2022-01-04
ZHEJIANG UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, my country's domestic economy has developed rapidly, which has improved people's living standards and quality to a certain extent, and the industrial level has undergone tremendous changes compared with the past. However, while ensuring production efficiency, inaccurate positioning of product locations affects many industrial manufacturers
The mouth of the filter bag plays an important role in the intelligent production process of the filter bag. However, due to the flexibility of the filter bag, the traditional target detection method is difficult to achieve and the detection accuracy cannot meet the production requirements of the factory.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Filter bag mouth position detection method based on depth separable convolution YOLOv4 model
  • Filter bag mouth position detection method based on depth separable convolution YOLOv4 model
  • Filter bag mouth position detection method based on depth separable convolution YOLOv4 model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments, and the purpose and effect of the present invention will become clearer. It should be understood that the specific embodiments described here are only used to explain the present invention and are not intended to limit the present invention.

[0039] The principle of the present invention is as follows: firstly collect pictures of the mouth of the filter bag, perform data enhancement on the pictures, and mark all the obtained pictures, and divide them into a training set, a verification set and a test set. Then build a YOLOv4 target detection model based on depth separable convolution, use the output of the K-means++ clustering algorithm as the initial prior frame size of the YOLOv4 target detection model based on depth separable convolution, and replace the feature extraction network with MobileNetV3 neural network with smaller total parameters....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a filter bag mouth position detection method based on a depth separable convolution YOLOv4 model. The method comprises the steps of firstly, collecting a filter bag mouth picture on a conveying belt through a camera; then performing data enhancement on all the pictures, labeling the images, and constructing a filter bag mouth data set; constructing a YOLOv4 target detection model based on depth separable convolution, setting training parameters, and training the YOLOv4 target detection model based on depth separable convolution by using the filter bag mouth data set; and finally, inputting the to-be-detected filter bag mouth picture into the trained YOLOv4 target detection model based on depth separable convolution, and outputting the to-be-detected filter bag mouth picture marked with the position of the detection frame and the category of the filter bag mouth. According to the method, the total parameter number of the model is reduced, and the calculation speed of the model is increased.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to the field of image detection and recognition, in particular to a method for detecting the position of a filter bag mouth based on a depth-separable convolution YOLOv4 model. Background technique [0002] In recent years, my country's domestic economy has developed rapidly, which has improved people's living standards and quality to a certain extent, and the industrial level has undergone tremendous changes compared with the past. However, while ensuring production efficiency, the inaccurate positioning of product locations affects with many industrial manufacturers. The mouth of the filter bag plays an important role in the intelligent production process of the filter bag. However, due to the flexibility of the filter bag, the traditional target detection method is difficult to achieve and the detection accuracy cannot meet the production requirements of the factory. Therefore, an ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23213G06F18/214
Inventor 王宪保余皓鑫周宝陈科宇雷雅彧翁扬凯
Owner ZHEJIANG UNIV OF TECH