一种视觉检测的智能适配方法、装置及电子设备
By combining the brightness and depth contrast of two-dimensional template images and three-dimensional template point clouds, and intelligently selecting visual detection algorithms, the problems of high labor costs and low detection accuracy in existing technologies are solved, and efficient three-dimensional structure detection is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LCFC HEFEI ELECTRONICS TECH
- Filing Date
- 2022-12-06
- Publication Date
- 2026-07-17
AI Technical Summary
In the detection of defects in three-dimensional structural components, existing technologies require a large amount of manpower for training neural networks based on two-dimensional images, while methods based on three-dimensional point clouds are less effective for detecting areas with small height differences. Therefore, intelligently selecting the optimal detection algorithm is crucial.
By acquiring two-dimensional template images and three-dimensional template point clouds, the brightness contrast and depth contrast of the region to be tested are determined, thereby selecting a suitable visual detection algorithm, including two-dimensional visual detection, three-dimensional visual detection, or a combination of both.
It reduces the workload of modeling, improves the effect of 3D structure detection, makes up for the shortcomings of 2D image and 3D point cloud methods, and improves detection accuracy.
Smart Images
Figure CN115861240B_ABST