Abstract
This thesis addresses the problem of real-time 3D localization and mapping in underwater environments.In the underwater archaeology field, Remotely Operated Vehicles (ROVs) are used to conduct deep-seasurveys and excavations. Providing both accurate localization and mapping information in real-time iscrucial for manual or automated piloting of the robots. While many localization solutions already existfor underwater robots, most of them rely on very accurate sensors, such as Doppler velocity logs or fiberoptic gyroscopes, which are very expensive and may be too bulky for small ROVs. Acoustic positioningsystems are also commonly used for underwater positioning, but they provide low frequencymeasurements, with limited accuracy.In this thesis, we study the use of low-cost sensors for accurate underwater localization. Our studyinvestigates the use of a monocular camera, a pressure sensor and a low-cost MEMS-IMU as the onlymeans of performing localization and mapping in the context of underwater archaeology.We have conducted an evaluation of different features tracking methods on images affected by typicaldisturbances met in an underwater context. From the results obtained with this evaluation, we havedeveloped a monocular Visual SLAM (Simultaneous Localization and Mapping) method, robust to thespecific disturbances of underwater environments. Then, we propose an extension of this method totightly integrate the measurements of a pressure sensor and an IMU in the SLAM algorithm. The finalmethod provides a very accurate localization and runs in real-time. In addition, an online dense 3Dreconstruction module, compliant with a monocular setup, is also proposed. Two lightweight and compactprototypes of this system have been designed and used to record datasets that have been publiclyreleased. Furthermore, these prototypes have been successfully used to test and validate the proposedlocalization and mapping algorithms in real-case scenarios.