A Robotic Line Scan System with Adaptive ROI for Inspection of Defects over Convex Free-form Specular Surfaces
This addresses the challenge of inspecting defects on complex reflective surfaces for manufacturing or quality control, but it appears incremental as it builds on existing robotic and vision techniques.
The paper tackles the problem of defect inspection on free-form specular surfaces by developing a robotic system that segments surfaces using K-means, adapts scanning paths, and uses a novel registration method, achieving validation through experimental studies.
In this paper, we present a new robotic system to perform defect inspection tasks over free-form specular surfaces. The autonomous procedure is achieved by a six-DOF manipulator, equipped with a line scan camera and a high-intensity lighting system. Our method first uses the object's CAD mesh model to implement a K-means unsupervised learning algorithm that segments the object's surface into areas with similar curvature. Then, the scanning path is computed by using an adaptive algorithm that adjusts the camera's ROI to observe regions with irregular shapes properly. A novel iterative closest point-based projection registration method that robustly localizes the object in the robot's coordinate frame system is proposed to deal with the blind spot problem of specular objects captured by depth sensors. Finally, an image processing pipeline automatically detects surface defects in the captured high-resolution images. A detailed experimental study with a vision-guided robotic scanning system is reported to validate the proposed methodology.