Robust real-time detection of an underwater pipeline

Primo Zingaretti+ and Silvia Maria Zanoli*

Abstract

Currently, methods for the inspection of underwater structures adopts remote operated vehicles guided from a support vessel by human operators. The risk of loosing concentration calls for the development of an intelligent vision, guidance and control system to support the human activity. The paper presents a robust system for the detection and the real-time tracking of submarine pipelines. An active vision system is proposed to predict changes in the scene and to direct computational resources to confirm expectations by adapting the processing mode dynamically. The system originates from an image processing algorithm that was previously developed by the authors to recognise the pipeline in the image plane. The accuracy of this algorithm has been enhanced by exploiting the temporal context in the image sequence. Disturbances of motion effect on acquired images are partially removed by a Kalman filter. The filter results advantageous in supporting the guide and the control of the ROV and in making more robust the image processing module itself. Sequences of underwater images, acquired at a constant sampling frequency from tv-cameras, are used together with synchronised navigation data to demonstrate the effectiveness of the system.

Keywords

Underwater vision, Remote operated vehicle (ROV), Image understanding, Object tracking, Vision-based guidance, Active vision, Real-time imaging, Kalman filter.