Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Philip Heller
Second Advisor
Nada Attar
Third Advisor
Maya deVries
Keywords
Crustose Coralline Algae (CCA), ARMS (Autonomous Reef Monitoring Structures), Mask R-CNN
Abstract
Coral reefs, made up of thousands of polyps - tiny sac-like marine invertebrates sea anemones and jellyfish, are important to marine ecosystems and prevent loss of life by acting as a natural barrier against storms, floods, and waves. These reefs support a wide range of species, many of which are underexplored and new species being discovered regularly. Crustose coralline algae (CCA) is one of the vital algal species that provides reef structure. Studying the abundance of CCA is important in helping marine biologists analyze coral reef health while understanding the impact of climate change on the marine lifeforms. This study aims to find the presence of CCA via segmenting images of ARMS (Autonomous Reef Monitoring System) plates - artificial structures used to study marine biodiversity - utilizing the state-of-the-art Mask Region-based Convolutional Neural Network (Mask R-CNN) algorithm. Mask R-CNN is a widely used algorithm for instance segmentation, capable of identifying and localizing objects in images while accurately delineating pixel-level boundaries for each instance, making it ideal for segmenting CCA. The results demonstrate the potential of deep learning in marine species segmentation, highlighting areas for improvement in dataset quality and model generalization while also paving the way for more accurate marine ecosystem monitoring.
Recommended Citation
Deshpande, Vrushali Harshwardhan, "Detecting Crustose Coralline Algae (CCA) in Marine Photos using Mask R-CNN" (2024). Master's Projects. 1446.
https://scholarworks.sjsu.edu/etd_projects/1446
