Automated open circuit scuba diver detection with low cost passive sonar and machine learning
Cole, Andrew M.
MetadataShow full item record
This thesis evaluates automated open-circuit scuba diver detection using low-cost passive sonar and machine learning. Previous automated passive sonar scuba diver detection systems required matching the frequency of diver breathing transients to that of an assumed diver breathing frequency. Earlier work required prior knowledge of both the number of divers and their breathing rate. Here an image processing approach is used for automated diver detection by implementing a deep convolutional neural network. Image processing was chosen because it is a proven method for sonar classification by trained human operators. The system described here is able to detect a scuba diver from a single acoustic emission from the diver. Twenty dives were conducted in support of this work at the WHOI pier from October 2018 to February 2019. The system, when compared to a trained human operator, correctly classified approximately 93% of the data. When sequential processing techniques were applied, system accuracy rose to 97%. This demonstrated that a combination of lowcost, passive sonar and a properly tuned convolutional neural network can detect divers in a noisy environment to a range of at least 12.49 m (50 feet).
Submitted in partial fulfillment of the requirements for the degree of Master of Science in Mechanical Engineering at the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution June 2019.
Suggested CitationThesis: Cole, Andrew M., "Automated open circuit scuba diver detection with low cost passive sonar and machine learning", 2019-06, DOI:10.1575/1912/24459, https://hdl.handle.net/1912/24459
Showing items related by title, author, creator and subject.
Bennett, Sara L. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1988-09)The highly energetic Agulhas Retroflection region south of the African continent lies at the junction of the South Indian, South Atlantic, and Circumpolar Oceans. A new survey of the Agulhas Retroflection taken in March ...
Kading, Tristan (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2013-02)Thiol substances can form stable complexes with metals (especially copper and mercury) in the surface ocean that can impact cycling and bioavailability of those elements. In this study, I present seven concentration ...
DuRand, Michele D. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1995-09)A number of investigators have observed diel variations in the bulk water inherent optical property beam attenuation, with a minimum near dawn and a maximum near dusk, and have assumed them to be caused by the phytoplankton. ...