基于外参调整的平面成像透视变形校正方法

By adjusting the extrinsic parameters of a monocular camera to generate ideal, perspective-free points and establishing a perspective transformation model, the problem of measurement inaccuracy caused by perspective distortion of the target plane is solved. This achieves the preservation of image plane proportions and distance scales, and improves measurement accuracy and stability.

CN118037605BActive Publication Date: 2026-07-17TIANJIN UNIV

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TIANJIN UNIV
Filing Date
2024-02-27
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies cause perspective distortion when the target plane is not perpendicular to the camera's optical axis, affecting the accuracy and stability of measurement results. Furthermore, manually setting an ideal point without perspective distortion makes it difficult to maintain the aspect ratio and relative distance scale of the plane.

Method used

By calibrating the intrinsic parameters and distortion coefficients of a monocular camera, the checkerboard corner points of the perspective distortion image are detected, the out-of-plane parameters are calculated and the rotation matrix is ​​adjusted to generate ideal perspective distortion-free points, a perspective transformation model is established and the model parameters are optimized to achieve perspective distortion correction.

Benefits of technology

It effectively maintains the aspect ratio of the image plane and the relative camera distance scale, improves the accuracy and stability of the pixel equivalent method, and realizes perspective distortion correction under arbitrary configuration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118037605B_ABST
    Figure CN118037605B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于外参调整的平面成像透视变形校正方法,该方法先由一台单目相机对目标平面下的一幅二维平面标靶进行拍摄,得到标靶的透视变形图像;然后对该透视变形图像角点检测得到实际透视变形点;另根据平面成像的单应性原理计算平面外参数并采用罗德里格斯公式对所得外参数进行调整以生成理想无透视变形点;进而以所述实际透视变形点和对应理想无透视变形点偏差最小为目标建立图像透视变换模型并求解模型参数;最后基于所述透视变换模型对目标平面下的任意透视变形图像进行透视变形校正。该方法克服了目标平面与相机光轴垂直度较差时产生的透视变形问题,且校正后的图像保持了平面的长宽比例以及平面相对相机的距离尺度。
Need to check novelty before this filing date? Find Prior Art