2025 ASEE Annual Conference & Exposition

BOARD #130: AI-Driven Mussel Behavior Monitoring Using An Accessible 3D Imaging System

Presented at Poster Session-Electrical and Computer Engineering Division (ECE)

Mussels play a crucial role in monitoring and reducing water pollution. As natural bio-indicators, they filter pollutants such as heavy metals, providing a sustainable method for water decontamination. This project leverages AI to monitor mussel behavior, particularly their gaping activity, to enhance the water purification process. We aim to employ advanced 3D reconstruction techniques to create detailed models of mussels, improving the accuracy of AI-based analysis. Specifically, we use a state-of-the-art 3D reconstruction tool, Neural Radiance Fields (NeRF), to create 3D models for analyzing mussel configurations and behavioral patterns. NeRF enables 3D reconstruction of scenes and objects from a sparse set of 2D images. To capture these images, we develop a data collection system capable of photographing mussels from multiple viewpoints. The system featured a turntable made of foam board, marker around the edges, with a designated space in the center for the mussels. The turntable was attached to a servo motor controlled by an ESP32 microcontroller. It rotated in 10-degree increments, with the ESP32 camera capturing an image at each step. The images, along with degree information and timestamps, are stored on an SD card. Several components, such as the camera holder and turntable base, are 3D printed. These images are used to train a NeRF model using the Python-based NerfStudio framework, and the resulting 3D models are viewed via the NerfStudio API. The setup is designed to be user-friendly, making it easy for students, including K-12-aged students, to create 3D reconstructions of their chosen objects. Both the embedded hardware and software are simple to build and implement. In the summer of 2024, a team of high school students from the Juntos Academy at NC State worked on this platform, gaining hands-on experience in embedded hardware development, basic machine learning principles, and 3D reconstruction from 2D images.

Authors
  1. Mr. Mayur Sanap North Carolina State University at Raleigh [biography]
  2. Arman Badalamenti North Carolina State University at Raleigh [biography]
  3. Devadharshini Ayyappan North Carolina State University at Raleigh [biography]
  4. Sanjana Banerjee North Carolina State University at Raleigh [biography]
  5. Mrs. Diana Milena Urieta North Carolina State University at Raleigh [biography]
  6. Dr. Caren Cooper North Carolina State University at Raleigh [biography]
  7. Prof. Michael Daniele North Carolina State University at Raleigh [biography]
  8. Dr. James Reynolds North Carolina State University at Raleigh [biography]
  9. Jay F Levine North Carolina State University at Raleigh [biography]
  10. Prof. Alper Bozkurt North Carolina State University [biography]
Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025