Development of visual inspection robot based on motion and mind behaviors of expert inspector

In this research, we developed a visual inspection robot with human consciousness of attention based on body and sight motions. This robot could inspect cast metal object that is irregular both in illumination reflection and surface structure. We capture in advance images of body and sight motions of inspector performance by using 3D motion capture system and gaze analysis system, and analyzed the images for extracting expert skill through the consciousness of attention and concentration of inspection. Based on the consciousness model of inspection, we developed an inspection robot system with a smart mechanism of camera work and ROI control and finally dynamic image processing mechanism for rough detection and precise examination of defects.