Master of Science (MS)
computer vision, OpenCV, deep learning, machine learning, unsupervised learning, artificial neural networks, image processing, autonomous reef monitoring structures, coral reef, biodiversity, Census of Marine Life
The preservation of the world’s oceans is crucial to human survival on this planet, yet we know too little to begin to understand anthropogenic impacts on marine life. This is especially true for coral reefs, which are the most diverse marine habitat per unit area (if not overall) as well as the most sensitive. To address this gap in knowledge, simple field devices called autonomous reef monitoring structures (ARMS) have been developed, which provide standardized samples of life from these complex ecosystems. ARMS have now become successful to the point that the amount of data collected through them has outstripped the capacity of research organizations to analyze through molecular methods. To facilitate these efforts, the present study explores the use of computer vision techniques to analyze the complex image data of these samples in order to extract useful information based on morphological (visual) characteristics of the collected organisms. Various techniques at varying levels of sophistry are surveyed for their suitability to the present problem. In the end, the more complex techniques are ruled out in the favor of basic image processing ones, of which three are tested: canny edge detection, color space transformations, and histogram equalization. While the first one does not directly yield useful results, the latter two turn out to be surprisingly effective, showing great promise as means to prepare data that more sophisticated techniques can be subsequently trained on. Future directions of investigation are recorded in detail, along with suggestions and relevant references, towards ultimately realizing an online analysis tool and repository for marine life that would accelerate related research and conservation efforts.
Bhodia, Niket, "Using Computer Vision to Quantify Coral Reef Biodiversity" (2019). Master's Projects. 711.