Imaging sonar simulator for assessment of image registration techniques

This work focuses on building a Forward-Looking sonar simulator capable of generating large volumes of ground truth data to test algorithms such as: novel image registration techniques for trajectory estimation, three-dimensional reconstruction or to be used as training data for machine learning algorithms. The simulator is capable of generating realistic data sets of images and providing ground truth data with the exact position and attitude of the sonar related to objects in a test scenario. The sonar simulator is developed using the Unity software platform. This work also shows an example application. Simulated image data sets for different sonar trajectories and seabed textures were created. These data sets are used by an attitude-trajectory estimation method and a quantitative analysis of the method is presented.