MBARI creates and globally scales the visionary technologies required to explore, map, and understand our changing ocean.
Resources for educators, students, and anyone aspiring to learn how science and technology brings us closer to the ocean.
Integrate MBARI data with lesson plans and workshops.
Discover deep-sea critters, including exclusive footage and info.
Dive into topics about ocean health and its fascinating features.
Explore deep-sea observations with this interactive guide.
Learn about the MLML/MBARI Research Library.
Access more educational resources from the teams at MBARI.
MBARI is a non-profit oceanographic research center advancing marine science and engineering to understand our changing ocean.
Learn about MBARI’s mission, vision, and values.
Learn about our strategic priorities for the years ahead.
Meet our staff, leadership, and board of directors.
Find job openings and postdoc and internship opportunities.
Follow MBARI on social media and stay updated.
See upcoming seminars, lectures, and public events.
Access the latest annual reports and financial information.
Explore MBARI’s rich history spanning over three decades.
Get media-specific information and assets.
Find the latest job openings and join the team.
Learn about our summer internship program.
Meet our leadership and staff.
Discover deep-sea critters of all types.
Search MBARI’s library of data.
Learn about our technologies.
MBARI’s Video Lab has made significant advancements towards incorporating machine learning (ML) into the annotation and analysis of our 38-year archive of deep-sea video. Central to these efforts is the integration of the Video Annotation and Reference System (VARS) with advanced ML tools and the development of a new machine-assisted annotation workflow (VARS-ML).
Over 28,000 hours of deep-sea video footage recorded since 1987.
More than 500,000 frame grabs available for quick review, reference, and revision.
Over 10 million annotations of marine life, habitats, science experiments, and phenomena.
VARS-ML has generated over 690,000 localizations—crucial to model training—of 1,600 unique classes.
We retrain our models using an iterative approach. With each iteration, our models become more accurate by including more and/or better localized training data. Our goals are twofold: to improve model performance and to decrease the time required for human validation. We believe that in the future this dynamic process will allow us to better handle the immense scale of our expanding video archives while maintaining or enhancing scientific value. Machine learning will also open up opportunities for data mining of the older footage in the archives, enabling us to refine and update observations and to explore undiscovered findings from the past.
Model training in the cloud | Ultralytics YOLO models:
MBARI uses Ultralytics YOLO models to train our machine learning algorithms. These models are optimized for object detection and identification, allowing them to recognize marine species, equipment, and other features with high precision. Cloud computing resources are used to train large models more quickly and efficiently.
Model inferencing | Generating ML proposals using cloud compute, local GPU, or desktop computers:
Once trained, the models generate proposals (model inferencing)—computer-generated and automated annotations of objects in new video or image datasets. We can run inferencing on cloud compute, local GPU, or desktop computers, depending on the size of the dataset and the speed required. This allows for flexibility when processing new data. In the near future, we will be able to run inferencing during ROV dives in real time.
The VARS team has developed custom applications to streamline the localization and validation processes, making it more efficient to generate training datasets and validate results. These innovations are central to our success in applying machine learning to marine science.
VARS Annotation:
The VARS Annotation GUI, with its custom Sharktopoda video player, allows us to localize directly on video during our normal annotation process. To our knowledge, Sharktopoda was the first standalone video player built with this capacity. An integrated model (VARS-oracle) enables us to generate ML proposals on-the-fly while using VARS.
VARS-localize:
VARS-localize allows us to search for existing frame grabs and rapidly localize objects for generating ML additional model training data.
VARS-gridview:
VARS-gridview is used to review, edit, and validate ML and human-generated localized regions of interest (ROIs). We can sort ROIs by class label, observer, dive number, and visual similarity.
Example of MBARI452k model object detection and tracking (Labels = ID number + class label + confidence level)
MBARI is committed to utilizing cutting-edge technology to advance marine research, ultimately providing critical insights into ocean health and ecosystems while fostering collaboration among scientists. The VARS-ML project combines the expertise of marine scientists, engineers, and data scientists to unlock the potential of machine learning in deep-sea research. This approach not only enhances our understanding of ocean ecosystems but also sets the stage for groundbreaking discoveries in the near future.