Cigarette micropore target detection method and system

CN119624933APending Publication Date: 2025-03-14CHINA TOBACCO YUNNAN IND
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411772923.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-04
Publication Date
2025-03-14

AI Technical Summary

Technical Problem

The different size and depth of cigarette punching seriously affect the tar content in mainstream flue gas, and the identification and detection accuracy of cigarette punching holes is low, which directly affects the calculation accuracy of punching morphological parameters, bringing challenges to the segmentation detection task of cigarette punching holes and subsequent hole depth measurement.

Method used

A cigarette micropore object detection method is adopted, and precise segmentation and hole depth measurement of cigarette punched areas are achieved through three-dimensional point cloud data acquisition, filtering processing, optimization of PointNet++ deep network model and introduction of Focal Loss function.

Benefits of technology

The identification and detection accuracy of cigarette punching is improved, and the accuracy of segmentation accuracy and hole depth measurement is achieved, which solves the problem of low calculation accuracy of hole punching morphological parameters. It is suitable for cigarette punching detection of different grades and hole numbers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119624933A_ABST
    Figure CN119624933A_ABST
Patent Text Reader

Abstract

The invention discloses a cigarette micropore target detection method and system, and belongs to the technical field of cigarette quality detection, and the method comprises the steps: carrying out the three-dimensional point cloud data collection of cigarettes of a plurality of brands, carrying out the filtering processing of collected cigarette punching original point cloud images, and removing useless background information; fusing feature information of different levels of cigarette punching original point cloud images, introducing a data adjustment function to fully train hole data in the feature information, and obtaining an optimized PointNet + + deep network model; and extracting point cloud data of the cigarette punching area, segmenting the whole predicted point cloud image according to the feature information of the distance between points, mapping the connection and edge contour of all points of the single hole into a two-dimensional image, and obtaining the maximum depth value of the to-be-detected hole. According to the method, the perforation segmentation and perforation depth calculation of cigarettes of various brands are realized, and a more efficient, convenient and reliable detection scheme is provided for cigarette production.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Container ship binding eye plate identification method

    CN120543932A