Visual calibration method, paint defect detection method, medium, and device

By using a visual calibration method, the initial extrinsic parameters and global precise extrinsic parameters between each acquisition device are determined, which solves the problem of insufficient positioning accuracy of vehicle body surface defect detection equipment and achieves efficient and high-precision defect detection.

CN122289400APending Publication Date: 2026-06-26SPEEDBOT ROBOTICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SPEEDBOT ROBOTICS CO LTD
Filing Date
2026-03-31
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

In existing automotive painting production, the surface defect detection equipment for car bodies suffers from insufficient positioning accuracy, resulting in low detection efficiency and poor accuracy, making it difficult to meet the demand for high-efficiency and high-quality detection.

Method used

By using a visual calibration method, the initial extrinsic parameters and global precise extrinsic parameters between each acquisition device are determined. An objective optimization function for the extrinsic parameters is constructed, and the precise extrinsic parameters between each acquisition device are solved to achieve accurate positioning of defects on the vehicle body surface.

Benefits of technology

It improves the accuracy and efficiency of vehicle body surface defect detection, meets the automotive manufacturing industry's demand for high-quality and high-efficiency inspection, and improves the compatibility and accuracy of inspection equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122289400A_ABST
    Figure CN122289400A_ABST
Patent Text Reader

Abstract

This invention relates to a visual calibration method, a paint defect detection method, a medium, and equipment. It involves acquiring several sets of vehicle body images and calibration images from different vehicle body positions; determining initial extrinsic parameters between each acquisition device based on the calibration images; identifying a master acquisition device and slave acquisition devices based on vehicle body feature points in the vehicle body images; determining the master precise extrinsic parameters between the master acquisition device coordinate system and the vehicle body coordinate system based on the 3D and 2D coordinates of the feature points; constructing an extrinsic parameter objective optimization function with the objective of minimizing the sum of squared pose deviations between the initial extrinsic parameters and the global precise extrinsic parameters, and solving for the global precise extrinsic parameters between each acquisition device; and obtaining the precise extrinsic parameters between the coordinate systems of each acquisition device and the vehicle body coordinate system based on the master precise extrinsic parameters and the global precise extrinsic parameters. This invention solves the problems of low efficiency, poor accuracy, insufficient compatibility, and limited precision in existing technologies for detecting automotive paint defects.
Need to check novelty before this filing date? Find Prior Art