A cigarette case counting leak-proof scanning intelligent system
The layered architecture of the intelligent cigarette box counting system, combined with industrial cameras and AI vision counting modules, solves the problems of accuracy and missed detection in cigarette box counting on the tobacco logistics conveyor line, achieving low-cost, uninterrupted, efficient deployment and accurate counting.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA TOBACCO GENERAL CO JIANGXI CO
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-21
AI Technical Summary
In existing tobacco logistics finished product conveying lines, the cigarette box counting system suffers from problems such as IO trigger counting distortion, insufficient identification of scanning blind spots, frequent communication anomalies, and highly invasive system modification, resulting in inaccurate missed scan detection and high modification costs.
It adopts a layered architecture consisting of a perception layer, an edge computing layer, a control execution layer, and a human-machine interaction layer. It utilizes industrial cameras and fixed barcode scanners combined with an AI vision counting module, and uses YOLO target detection algorithm and multi-target tracking algorithm to identify and count cigarette boxes. The fusion comparison and judgment module verifies the actual number of boxes in real time, the IO control module drives the action of the actuator, and the human-machine interaction layer provides the operation interface.
It achieves improved accuracy in cigarette box counting without interrupting production and at low cost, solves the core defects of IO-triggered counting distortion and missed detection, enhances the maintainability and scalability of the system, and improves the counting accuracy and the accuracy of missed detection.
Smart Images
Figure CN122433775A_ABST