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
Fabio Di Troia
Third Advisor
Maya DeVries
Keywords
computer vision, deep learning, autonomous image reef monitoring structures, coral reef
Abstract
Crustose coralline algae (CCA) are a group of red algae that are vital contributors to the health of coral reef ecosystems. Monitoring CCA abundance can serve as an indicator for coral reef health and improve reef conservation efforts. Autonomous Reef Monitoring Structures (ARMS) are artificial structures that can be deployed into coral reef ecosystems and retrieved to gather ecological data without harming reef structures. Traditional methods of calculating CCA abundance require manual analysis and are labor-intensive. Recent developments in computer vision and deep learning technology have provided an avenue to fully automate this task. This research aims to train a machine learning model capable of automatically segmenting CCA in ARMS plate images by applying the Mask R-CNN algorithm. To accomplish this, ARMS plate images were annotated and used to create datasets. Numerous models were trained using varying parameters and datasets to establish best practice training methods. The best performing model in this work achieved, 0.6903 precision, 0.5538 recall, and an F1 score of 0.6146. These results demonstrate preliminary success with using the Mask-R CNN framework to identify CCA, showing potential for automatic CCA coverage calculation.
Recommended Citation
Tseng, Ryan, "Coral Vision – Crustose Coralline Algae Detection with Computer Vision" (2025). Master's Projects. 1474.
DOI: https://doi.org/10.31979/etd.d659-7qmn
https://scholarworks.sjsu.edu/etd_projects/1474
