Is AI currently capable of identifying wild oysters? A comparison of human annotators against the AI model, ODYSSEE

Campbell Brendan , Williams Alan , Baxevani Kleio , Campbell Alyssa , Dhoke Rushabh , Hudock Rileigh E. , Lin Xiaomin , Mange Vivek , Neuberger Bernhard , Suresh Arjun , Vera Alhim , Trembanis Arthur , Tanner Herbert G. , Hale Edward

doi:10.3389/frobt.2025.1587033

i

Is AI currently capable of identifying wild oysters? A comparison of human annotators against the AI model, ODYSSEE

2025
By Campbell Brendan , Williams Alan , Baxevani Kleio , Campbell Alyssa , Dhoke Rushabh , Hudock Rileigh E. , Lin Xiaomin , Mange Vivek , Neuberger Bernhard , Suresh Arjun , Vera Alhim , Trembanis Arthur , Tanner Herbert G. , Hale Edward

Select the Download button to view the document

Please click the download button to view the document.

Details

Journal Title:

Frontiers in Robotics and AI
Personal Author:

Campbell Brendan , Williams Alan , Baxevani Kleio , Campbell Alyssa , Dhoke Rushabh , Hudock Rileigh E. , Lin Xiaomin , Mange Vivek , Neuberger Bernhard , Suresh Arjun , Vera Alhim , Trembanis Arthur , Tanner Herbert G. , Hale Edward
NOAA Program & Office:

OAR (Oceanic and Atmospheric Research)
Description:

Oysters are ecologically and commercially important species that require frequent monitoring to track population demographics (e.g., abundance, growth, mortality). Current methods of monitoring oyster reefs often require destructive sampling methods and extensive manual effort. However, these methods are destructive and are suboptimal for small-scale or sensitive environments. A recent alternative, the ODYSSEE model, was developed to use deep learning techniques to identify live oysters using video or images taken in the field of oyster reefs to assess abundance. The validity of this model in identifying live oysters on a reef was compared to expert and non-expert annotators. In addition, we identified potential sources of prediction error. Although the model can make inferences significantly faster than expert and non-expert annotators (39.6 s, 2.34±0.61 h, 4.50±1.46 h, respectively), the model overpredicted the number of live oysters, achieving lower accuracy (63%) in identifying live oysters compared to experts (74%) and non-experts (75%) alike. Image quality was an important factor in determining the accuracy of the model and annotator. Better quality images improved human accuracy and worsened model accuracy. Although ODYSSEE was not sufficiently accurate, we anticipate that future training on higher-quality images, utilizing additional live imagery, and incorporating additional annotation training classes will greatly improve the model’s predictive power based on the results of this analysis. Future research should address methods that improve the detection of living vs dead oysters.
Keywords:

Deep Learning (Machine Learning) Oysters Reef Ecology Deep Learning (Machine Learning) Reef Ecology Confusion Matrix Image Identification Oyster Aquaculture Oyster Reefs YOLOv10
Source:

Front. Robot. AI 12:1587033
DOI:

https://doi.org/10.3389/frobt.2025.1587033
Format:

PDF
Document Type:

Journal Article
License:

https://creativecommons.org/licenses/by/4.0/
Rights Information:

CC BY
Compliance:

Submitted
Main Document Checksum:

urn:sha-512:9505ed8148d825b6568310b00d87508ea13c6d7bbd95bb94b049b0464e6e2404001ba3b9c31bb0691239ca8bce372663cd87e6a4662d6d9b5a6b2a6d6a67118d
Download URL:

https://repository.library.noaa.gov/view/noaa/71700/noaa_71700_DS1.pdf
File Type:

[PDF - 24.24 MB ]

ON THIS PAGE

Details

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.