EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OpenApePose, a database of annotated ape photographs for pose estimation

Nisarg Desai iD, Praneet Bala iD, Rebecca Richardson, Jessica Raper iD, Jan Zimmermann, Benjamin Hayden

eLife · 2023

DOI: 10.7554/elife.86873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eLife, 2023. Verfasst von Nisarg Desai und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience and Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, United States. Hauptthemen laut MEDLINE: Hominidae. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIMH NIH HHS, NIH HHS, NIDA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Because of their close relationship with humans, non-human apes (chimpanzees, bonobos, gorillas, orangutans, and gibbons, including siamangs) are of great scientific interest. The goal of understanding their complex behavior would be greatly advanced by the ability to perform video-based pose tracking. Tracking, however, requires high-quality annotated datasets of ape photographs. Here we present OpenApePose , a new public dataset of 71,868 photographs, annotated with 16 body landmarks of six ape species in naturalistic contexts. We show that a standard deep net (HRNet-W48) trained on ape photos can reliably track out-of-sample ape photos better than networks trained on monkeys (specifically, the OpenMonkeyPose dataset) and on humans ( COCO ) can. This trained network can track apes almost as well as the other networks can track their respective taxa, and models trained without one of the six ape species can track the held-out species better than the monkey and human models can. Ultimately, the results of our analyses highlight the importance of large, specialized databases for animal tracking systems and confirm the utility of our new ape database.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HominidaeAnimalsGorilla gorillaPan troglodytesHaplorhiniPan paniscusHylobates

Stichwörter der Autor:innen

apesbehavior trackingdatasetdeep learningneurosciencepose estimation

Autor:innen und Institutionen

  • Department of Neuroscience and Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, United States.
  • Department of Computer Science, University of Minnesota, Minneapolis, United States.
  • Emory National Primate Research Center, Emory University, Atlanta, United States.

ORCID-Profile: Nisarg Desai, Praneet Bala, Jessica Raper

Förderung

  • NIMH NIH HHS
  • NIH HHS
  • NIDA NIH HHS
  • National Institutes of Health
  • National Science Foundation
  • University of Minnesota
  • Minnesota Institute of Robotics
  • Emory National Primate Research Center

Zitieren

APA

Desai, N., Bala, P., Richardson, R., Raper, J., Zimmermann, J., & Hayden, B. (2023). OpenApePose, a database of annotated ape photographs for pose estimation. eLife. https://doi.org/10.7554/elife.86873

Vancouver

Desai N, Bala P, Richardson R, Raper J, Zimmermann J, Hayden B. OpenApePose, a database of annotated ape photographs for pose estimation. eLife. 2023. doi:10.7554/elife.86873

BibTeX
@article{Desai2023,
  author = {Desai, Nisarg and Bala, Praneet and Richardson, Rebecca and Raper, Jessica and Zimmermann, Jan and Hayden, Benjamin},
  title = {OpenApePose, a database of annotated ape photographs for pose estimation},
  journal = {eLife},
  year = {2023},
  doi = {10.7554/elife.86873}
}
Kostenlos starten →