基于自适应条纹投影的面结构光高反表面三维测量方法
By using an adaptive fringe projection method, combined with multimodal data and hierarchical region analysis, the problems of data loss and distortion in the 3D measurement of high-reflectivity objects were solved, and high-quality 3D point cloud reconstruction was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUILIN MEASURING & CUTTING TOOLS CO LTD
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing structured light 3D measurement technology suffers from compromised measurement quality and integrity when dealing with objects with high reflectivity or drastic changes in surface reflectivity. Camera sensor saturation or low signal-to-noise ratio can lead to data loss and distortion.
An adaptive fringe projection method is adopted. By projecting in stages and acquiring deformed image sequences, a multimodal benchmark dataset is extracted, and dual-path analysis and region division are performed to generate a global projection light intensity adaptive mask. Combined with iterative optimization, complete 3D point cloud data is generated.
It enables precise perception and control of highly reflective surfaces, maintains the integrity of texture details, improves the robustness and accuracy of 3D reconstruction, and obtains 3D point cloud data with high integrity and high reliability.
Smart Images
Figure CN122408663A_ABST