US-based marine geospatial provider Tcarta Marine has been awarded a National Science Foundation (NSF) grant to optimise seafloor depth measurements from optical satellite imagery.
The ‘Project Trident’ research seeks to automate and extend existing satellite derived bathymetry (SDB) techniques using machine learning and computer vision methodologies, aiming to enable accurate depth retrieval in variable water conditions.
Tcarta won the NSF grant in partnership with jOmegak and DigitalGlobe, in the first phase of the NSF Small Business Innovation Research program.
The research will develop a proprietary technique for digitally extracting water depth measurements down to 20 metres from high-resolution DigitalGlobe WorldView satellite imagery. The proposed new techniques will incorporate wave kinematics, a technique patented by jOmegak to calculate water depths in shallow waters by analyzing the patterns and speed of waves detected in satellite imagery.
“Our goal with Project Trident is to expand the geographic scope of SDB in shallow coastal areas,” said Kyle Goodrich, TCarta president. “SDB technology currently derives water depths only in calm, clear waters, which limits its applicability.”
“In the current SDB process, we use manual stereo photogrammetry methods to measure seafloor ground control points in digital satellite imagery, but this is extremely time consuming,” he said.
“We are developing an automated photogrammetric process to extract a greater number of ground truth points from high-resolution WorldView imagery.”
Stay up to date by getting stories like this delivered to your mailbox.
Sign up to receive our free weekly Spatial Source newsletter.