Cigarette filter stick counting method based on AA R2Unet and HMM

A counting method and cigarette filter technology, which are applied in neural learning methods, calculations, image data processing, etc., can solve problems such as target adhesion, camera field of view distortion, and can not be solved well, and achieve the improvement of detection accuracy and detection range. effect of progress

Pending Publication Date: 2020-11-03
NANTONG UNIVERSITY +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Batch-intensive target recognition often encounters problems such as adhesion between targets, low contrast between targets and background, targets blocked by shadows, and camera field of view distortion.
These problems seriously affect the accuracy of image recognition, and the current mainstream recognition methods cannot be solved well.

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
  • Cigarette filter stick counting method based on AA R2Unet and HMM
  • Cigarette filter stick counting method based on AA R2Unet and HMM
  • Cigarette filter stick counting method based on AA R2Unet and HMM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0045] see Figure 1-6 , the present invention provides a technical solution: the present invention provides the following technical solution: a method for counting cigarette filter rods based on AAR2Unet and HMM, comprising the following steps:

[0046] A. Establish an AA R2Unet network to segment the collected filter stick pictures to obtain images that only contain filter stick targets;

[0047] B. Optimal search algorithm based on HMM;

[0048] C. Count ...

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 cigarette filter stick counting method based on AA R2Unet and HMM, and the method carries out the training through a Unet network model, and accurately recognizes the targetand background of a filter stick. Therefore, according to the identified binary image, a structural unit filling and circle tangent searching strategy of the filter stick distribution characteristicsis provided, and an experimental result shows that the algorithm is greatly improved in detection precision and detection range.

Description

technical field [0001] The invention relates to the technical field of counting cigarette filter rods, in particular to a method for counting cigarette filter rods based on AA R2Unet and HMM. Background technique [0002] Industrial sites often need to accurately identify dense small targets in complex environments. In actual production, random sampling manual identification with low precision is still used for batch identification to ensure consistent quality specifications. Batch-intensive target recognition often encounters problems such as adhesion between targets, low contrast between targets and the background, targets blocked by shadows, and camera field of view distortion. These problems seriously affect the accuracy of image recognition, and the current mainstream recognition methods cannot be solved well. Contents of the invention [0003] The object of the present invention is to provide a method for counting cigarette filter rods based on AA R2Unet and HMM, s...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/143G06N3/08G06N3/02
CPCG06N3/02G06N3/08G06T7/0004G06T2207/20081G06T2207/20084G06T2207/30242G06T7/11G06T7/143
Inventor 张堃韩宇姜朋朋朱翊晗冯文宇殷佳炜华亮李文俊鲍毅
Owner NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap