3-D motion and depth estimation from sea-floor images for mosaic-based station-keeping and navigation of ROVs/AUVs and high-resolution sea-floor mapping

A vision system has been developed in order to support the autonomous operation or operated-assisted missions of AUV and ROV near the ocean bottom. The sea-floor images, acquired by a down-look camera installed on the vehicle, are processed by the vision system in order to detect and estimate its motion in real time. This information is utilized to realize a number of capabilities, including automatic station keeping, navigation and trajectory following, and the construction of a composite (mosaic) image of the sea floor. We describe the system and provide sample results from various experiments for evaluating performance. We also provide examples from ongoing work, planned for implementation on the real-time vision system.