Image-based Visual Servoing for Dynamic Positioning of a Work-Class ROV with Depth Computation

This paper presents a camera-in-hand configuration of an image-based visual servo controller to control dynamic positioning of a remotely operated vehicle (ROV) relative to a fixed target. To address the challenge of depth computation in IBVS, a novel approach that assumes knowledge of the distance between three feature points has been presented. Additionally, in order to bring the simulation results closer to reality a real camera was calibrated and its intrinsic parameters were used in the camera model. Finally, a proportional-integral-derivative (PID) controller was used to dynamically position an ROV. Using a work-class ROV, the proposed IBVS controller was demonstrated to be effective in dealing with uncertainties and external disturbances in the system.