Side-Scan Sonar Imaging: Automatic Boulder Identification

Boulder surveys seek to identify prominent boulders which position may collide with planned cable routes, offshore wind farms, or other subsea activities. Data is collected using suitable sensor technologies such as bathymetry from multibeam echosounders and side-scan sonar imaging. Currently, the boulder identification process is a labor-intensive job that requires domain expertise to interpret the data and provide each identified target with accurate annotations. In this work, we describe the initial steps of our method used for automatic boulder identification in side-scan data. This covers identifying each boulder instance and further generates metadata for filtering, sorting, and report generation. In addition to being an automated process, our method can process several kilometers of side-scan data and identify thousands of boulders in less than a minute. This is not only orders of magnitudes faster than human processors but also with great accuracy results.