USING DEEP LEARNING AND UAV IMAGERY TO DETECT ELKHORN CORAL IN ST. CROIX’S EAST END MARINE PARK

Author

Samuel WyattFollow

Date of Award

Spring 2022

Degree Type

Masters Thesis

Degree Name

Master of Science (MS)

School

Biological, Environmental, and Earth Sciences

Committee Chair

George Raber

Committee Chair School

Biological, Environmental, and Earth Sciences

Committee Member 2

Gregory Carter

Committee Member 2 School

Biological, Environmental, and Earth Sciences

Committee Member 3

Steve Schill

Abstract

Elkhorn coral, or Acropora palmata, is an important reef building species that promotes species abundance and other ecological services to the communities in the US Virgin Islands. We captured high resolution imagery of a reef in St. Croix’s East End Marine Park using a Wingtra One UAV. We then used deep learning techniques to detect individual coral colonies. We compared two deep learning models, FasterRCNN and MaskRCNN, and found that the models achieved accuracy shores up to 0.78. These scores improved when examining only larger corals in shallow waters. The model was able to both detect Elkhorn coral and distinguish it from other corals and features. This will be a useful method for measuring coral abundance and monitoring the success of restoration efforts.

Recommended Citation

Wyatt, Samuel, "USING DEEP LEARNING AND UAV IMAGERY TO DETECT ELKHORN CORAL IN ST. CROIX’S EAST END MARINE PARK" (2022). Master's Theses. 886.
https://aquila.usm.edu/masters_theses/886