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

What are Populations and Communities?00:30

What are Populations and Communities?

34.3K
Overview
34.3K

You might also read

Related Articles

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

Sort by
Same author

Scaling up ocean conservation through recognition of key biodiversity areas in the Southern Ocean from multispecies tracking data.

Conservation biology : the journal of the Society for Conservation Biology·2024
Same author

Seasonal acoustic presence of marine mammals at the South Orkney Islands, Scotia Sea.

Royal Society open science·2024
Same author

Wind-driven upwelling of iron sustains dense blooms and food webs in the eastern Weddell Gyre.

Nature communications·2023
Same author

Intra-season variations in distribution and abundance of humpback whales in the West Antarctic Peninsula using cruise vessels as opportunistic platforms.

Ecology and evolution·2022
Same author

The call of the emperor penguin: Legal responses to species threatened by climate change.

Global change biology·2021
Same author

Wintertime overlaps between female Antarctic fur seals (Arctocephalus gazella) and the krill fishery at South Georgia, South Atlantic.

PloS one·2021

Related Experiment Video

Updated: Aug 3, 2025

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K

Counting animals in aerial images with a density map estimation model.

Yifei Qian1, Grant R W Humphries2, Philip N Trathan3,4

  • 1School of Mathematics and Statistics University of St Andrews St Andrews Fife KY169AJ UK.

Ecology and Evolution
|April 11, 2023
PubMed
Summary

Automated counting of dense penguin colonies from aerial images is now possible. A new CNN-based density map method accurately counts penguins, improving wildlife monitoring from drone surveys.

Keywords:
abundance estimationdensity map estimationimage processingmachine learning

More Related Videos

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.3K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K

Related Experiment Videos

Last Updated: Aug 3, 2025

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.4K
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.3K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K

Area of Science:

  • Wildlife biology
  • Remote sensing
  • Computer vision

Background:

  • Animal abundance estimation increasingly relies on drone and aerial surveys.
  • Manual processing of large datasets is time-consuming and labor-intensive.
  • Automated counting is challenging for species nesting in close formations, like Pygoscelis penguins.

Purpose of the Study:

  • To develop and evaluate a customized Convolutional Neural Network (CNN)-based density map estimation method for counting penguins from low-resolution aerial photography.
  • To compare the accuracy of the proposed method against standard detection algorithms for small object counting in low-resolution images.

Main Methods:

  • A customized CNN model was developed for density map estimation.
  • The model was trained and tested on low-resolution aerial images of penguins.
  • Performance was evaluated by comparing counts against ground truth data and a Faster-RCNN model.

Main Results:

  • The CNN-based density map estimation method achieved a significantly lower error rate (0.8 percent) compared to the Faster-RCNN algorithm.
  • The indirect regression approach proved more effective for counting small objects in low-resolution imagery.
  • The method demonstrated high accuracy in counting penguins in tight aggregations.

Conclusions:

  • Density map estimation using customized CNNs offers a powerful and accurate solution for automated animal abundance estimation.
  • This approach can significantly improve the efficiency and accuracy of wildlife monitoring, especially for colonial nesters.
  • The findings support the broader application of density map estimation for analyzing aerial imagery in ecological studies.