Underwater Object Tracking with 2D Sonar Signals Preprocessed Using the Virtual High-Dynamic Range Enhancement Method

In this paper, a custom underwater 2D sonar signal acquisition, enhancement, and tracking system are presented. The system is based on a modern 2D multibeam sonar by Teledyne allowing data gathering and real-time operation. First, our custom setup allows 2D sonar signal acquisition for gathering underwater datasets, which are rare in the public domain. Second, two underwater object tracking methods are presented and tested, which are proposed to operate on the 2D sonar signal enhanced by the Virtual High-Dynamic Range (VHDR) method. It can modify sonar images by applying a number of tone-adjusting curves, potentially revealing hidden details. The tracking experiments were carried out on the original, as well as on the VHDR-processed data. Compared to original sonar images, the presented method decreased the tracking error by up to 26% and removed all tracking failures on preprocessed data. The presented system can also be easily customized, both from hardware and software points of view. Our created 2D sonar dataset is available free from the Internet and is planned to be expanded in the near future.