Rahul Thakur

Publication Date

Spring 2025

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Philip Heller

Second Advisor

Maya deVries

Third Advisor

Sayma Akther

Keywords

Mask R-CNN, Comparative analysis, machine learning algorithms, computer vision, coral reefs, CCA

Abstract

Coral reefs are an essential part of the marine ecosystem. They perform a wide variety of tasks, some directly and others indirectly. They can produce oxygen, absorb carbon dioxide, along with supporting ocean habitat. Crustose Coralline Algae (“CCA”) plays an important role in helping provide structural support to Coral Reef ecosystems. However, global warming is causing ocean water to become more acidic resulting in coral bleaching. This is leading to changes in coral environments and causing coral deaths at alarming rates. Object detection using computer vision techniques, specifically deep learning, can help to monitor coral reef health and identify CCA in reef structures over time. This project has performed CCA analysis using Mask R-CNN and findings conclude that a balanced solution is better at CCA detection than one that only focuses on high precision. Therefore, this project evaluated unique compositions of various Mask R-CNN models and found that a large training dataset with various ecosystems contributes to a more optimal and balanced CCA analysis.

Download

Available for download on Friday, May 15, 2026

Share

COinS