Python-based scroll recognition algorithm

Through the Python-based reel recognition algorithm, the circular end face of the material shaft is identified in real time and the center position is calculated, the accuracy and stability problems during the AGV docking of the cantilever shaft are solved, and the high accuracy and flexibility of the docking process are achieved.

CN119648794AActive Publication Date: 2025-03-18ZHUHAI MAKERWIT TECH CO LTD
6 Cites 0 Cited by

Patent Information

Application Number
CN202411791249.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-03-18
Estimated Expiration
2044-12-06

AI Technical Summary

Technical Problem

The prior art When the cantilever shaft AGV docks the material shaft, it is susceptible to the deformation of mechanical components and changes in material deviation, resulting in an increase in the risk of docking failure and cannot adapt to reel docking at different height positions.

Method used

Using Python-based reel recognition algorithm, through real-time image processing technology, the circular end face of the material shaft is identified, the center position is calculated, and the docking accuracy and stability are improved through dynamic deviation correction.

Benefits of technology

It improves the accuracy and stability of the docking process, is suitable for material shafts of different heights and types, is more flexible in docking, and the algorithm has good cross-platformity and portability.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a Python-based scroll recognition algorithm. The method comprises an image preprocessing step; a preliminary screening step; a secondary screening step: carrying out secondary screening on the primarily screened circular object list, and carrying out additional screening according to the relative positions of the circular objects; an intersection detection step; an overlapping detection step: performing overlapping detection on the circular objects after intersection detection, creating a binary mask image for each circular object, and then overlapping the mask images to search an overlapping region; an abnormal value processing step: carrying out abnormal value processing on the circular objects after overlapping detection to obtain a finally screened circular object list; scroll features are identified based on the final screened list of circular objects. According to the method, the circular end face of the material shaft can be accurately recognized, key data are provided for subsequent dynamic deviation correction, the precision and stability of the butt joint process are improved, and the method is suitable for butt joint of material shafts of different heights and types.
Need to check novelty before this filing date? Find Prior Art