Stereo Tracking and 3D Reconstruction of Underwater Pipes

Installing flexible oil pipes in deep underwater environments is a risky operation, which is currently monitored by manually comparing the geometric conditions to the simulated studies. In order to avoid this error-prone assessment, this paper proposes an algorithm to track and reconstruct the pipe medial axis using stereo cameras. By taking advantage of the scenario illumination and the pipe texture, it is possible to devise an energy maximization approach that efficiently tracks the pipe. The reconstruction technique is an enhancement over a state-of-the-art B-spline reconstruction algorithm, specializing it for plane curves. Experiments on synthetic and laboratory videos report a very low mean tracking and reconstruction errors, while there are strong evidences of the robustness on a real scenario.