Multipurpose optimization of camera position for robot vision by considering calibration accuracy

Recently, autonomous robots have been widely used in the production field. There are several advantages to introducing industrial robots in factories. However, these robots cannot be used in unknown environments because most of them are controlled by sequence controls. Two cameras are used as vision sensors that can recognize the outside environment to solve this problem. In this study, we aim at improving the camera calibration accuracies by two cameras. We know that calibration accuracies are affected by the positions of two cameras. Thus, we focus on the positions of the two cameras. Reducing the floor area of an industrial robot is expected to improve productivity. Thus, in this research, we propose the positions of two cameras in a small area by taking into consideration calibration accuracies. First of all, we examine the influences of the positions of two cameras for calibration accuracies. Next, we determine the optimal camera position from a simulation based on the modeling image noise obtained by experimentation. Finally, we verify the effectiveness of the positions of two cameras by a sorting operation. As a result, we can model the image noises of two cameras mathematically and determine the positions of the two cameras. Also, we can decrease the ranges of the cameras by 79.8%. In addition, the new camera positions improved the identification performance and handling performance.