Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Applying deep learning to right whale photo identification.

Conservation biology : the journal of the Society for Conservation Biology·2018
See all related articles

Related Experiment Video

Updated: Aug 9, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

707

Annotating very high-resolution satellite imagery: A whale case study.

Hannah Charlotte Cubaynes1, Penny Joanna Clarke1,2, Kimberly Thea Goetz3

  • 1British Antarctic Survey, High Cross, Madingley Road, Cambridge, CB3 0ET, United Kingdom.

Methodsx
|February 16, 2023
PubMed
Summary

This study presents a standardized workflow for annotating very high-resolution (VHR) satellite imagery of whales. This method facilitates the creation of AI-ready datasets for automated wildlife monitoring in understudied marine environments.

Keywords:
AI-ready dataCetaceanLabelingMachine learningSatellite image annotation to create point, bounding boxes and image datasets to train automated systems.VHR optical satellite imageWildlife

More Related Videos

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring
13:35

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Published on: June 13, 2025

538
A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
06:36

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

Published on: April 15, 2021

3.8K

Related Experiment Videos

Last Updated: Aug 9, 2025

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
09:19

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

707
Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring
13:35

Reefshape: A System for the Efficient Collection and Automated Processing of Time-Series Underwater Photogrammetry Data for Benthic Habitat Monitoring

Published on: June 13, 2025

538
A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry
06:36

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

Published on: April 15, 2021

3.8K

Area of Science:

  • Remote Sensing
  • Wildlife Ecology
  • Artificial Intelligence

Background:

  • Very high-resolution (VHR) optical satellite imagery offers potential for monitoring elusive species like whales in remote areas.
  • Automated target detection systems are crucial for analyzing large-scale VHR satellite datasets in wildlife research.
  • Machine learning models necessitate extensive, accurately annotated training datasets for effective development.

Purpose of the Study:

  • To establish a standardized protocol for annotating VHR optical satellite imagery for wildlife monitoring.
  • To develop a reproducible workflow for creating AI-ready datasets using cetaceans as a case study.
  • To guide the creation of bounding boxes and image chips for feature extraction from satellite data.

Main Methods:

  • Utilized ESRI ArcMap 10.8 and ArcGIS Pro 2.5 for image annotation.
  • Developed a step-by-step protocol for reviewing VHR images and annotating features of interest.
  • Implemented procedures for creating bounding boxes and clipping satellite images into chips.

Main Results:

  • A detailed, step-by-step protocol for annotating VHR satellite imagery was successfully created.
  • The workflow enables the generation of AI-ready annotations for machine learning applications.
  • Demonstrated the process of creating image chips for specific features of interest.

Conclusions:

  • The proposed standardized workflow effectively supports the annotation of VHR satellite imagery for wildlife studies.
  • This methodology is vital for advancing automated detection systems in marine wildlife monitoring.
  • Facilitates the development of robust AI models for analyzing large-scale ecological datasets.