3D reconstruction of shallow sea environment using direct system calibration and faint laser line extraction

Virtually recreating an underwater scene requires 3D data of its objects. Creating a dense 3D point cloud of shallow underwater objects using a laser in the presence of significant ambient light is challenging. Although several methodologies have been proposed for the same, they essentially work in low-light environments. In particular, current techniques are unable to quickly and effortlessly generate dense point clouds of underwater objects under varying light. This work fills that gap. It is based on triangulating a rotating low-power line-laser. It generates the point cloud online and automatically. It works in sunlight, which tends to washout low-power laser in shallow waters. To reduce the cumulative errors during calibration, our data-centric method calibrates the entire system directly, unlike the existing methods, where multiple parameters are calibrated separately. We also propose an analytical technique to segment faint-laser lines in an underwaterlit environment, which does not depend on the availability of large training data. An evaluation of the performance of the proposed method in different lightingconditions is reported.