EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using Computer Vision to Annotate Video-Recoded Direct Observation of Physical Behavior

Sarah K Keadle iD, Skylar Eglowski, Katie Ylarregui, Scott J Strath, Julian Martinez, Alex Dekhtyar iD, Vadim Kagan

Sensors · 2024

DOI: 10.3390/s24072359 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Sarah K Keadle und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Kinesiology and Public Health, California Polytechnic State University, San Luis Obispo, CA 93407, USA. Hauptthemen laut MEDLINE: Computers, Labor, Obstetric. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, National Institutes of Health, Small Business Innovation Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Direct observation is a ground-truth measure for physical behavior, but the high cost limits widespread use. The purpose of this study was to develop and test machine learning methods to recognize aspects of physical behavior and location from videos of human movement: Adults (N = 26, aged 18–59 y) were recorded in their natural environment for two, 2- to 3-h sessions. Trained research assistants annotated videos using commercially available software including the following taxonomies: (1) sedentary versus non-sedentary (two classes); (2) activity type (four classes: sedentary, walking, running, and mixed movement); and (3) activity intensity (four classes: sedentary, light, moderate, and vigorous). Four machine learning approaches were trained and evaluated for each taxonomy. Models were trained on 80% of the videos, validated on 10%, and final accuracy is reported on the remaining 10% of the videos not used in training. Overall accuracy was as follows: 87.4% for Taxonomy 1, 63.1% for Taxonomy 2, and 68.6% for Taxonomy 3. This study shows it is possible to use computer vision to annotate aspects of physical behavior, speeding up the time and reducing labor required for direct observation. Future research should test these machine learning models on larger, independent datasets and take advantage of analysis of video fragments, rather than individual still images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ComputersLabor, ObstetricAdultHumansPregnancyFemaleSoftwareEnvironmentMachine Learning

Stichwörter der Autor:innen

assessmentcomputer visiondirect observationphysical activitysedentary behavior

Autor:innen und Institutionen

  • Department of Kinesiology and Public Health, California Polytechnic State University, San Luis Obispo, CA 93407, USA.
  • Sentimetrix Inc., Bethesda, MD 20814, USA.
  • College of Public Health, University of Wisconsin, Milwaukee, WI 53205, USA.
  • Department of Computer Science and Software Engineering, California Polytechnic State University, San Luis Obispo, CA 93407, USA.

ORCID-Profile: Sarah K Keadle, Alex Dekhtyar

Förderung

  • NCI NIH HHS
  • National Institutes of Health, Small Business Innovation Research

Zitieren

APA

Keadle, S. K., Eglowski, S., Ylarregui, K., Strath, S. J., Martinez, J., Dekhtyar, A., & Kagan, V. (2024). Using Computer Vision to Annotate Video-Recoded Direct Observation of Physical Behavior. Sensors. https://doi.org/10.3390/s24072359

Vancouver

Keadle SK, Eglowski S, Ylarregui K, Strath SJ, Martinez J, Dekhtyar A, et al. Using Computer Vision to Annotate Video-Recoded Direct Observation of Physical Behavior. Sensors. 2024. doi:10.3390/s24072359

BibTeX
@article{Keadle2024,
  author = {Keadle, Sarah K and Eglowski, Skylar and Ylarregui, Katie and Strath, Scott J and Martinez, Julian and Dekhtyar, Alex and Kagan, Vadim},
  title = {Using Computer Vision to Annotate Video-Recoded Direct Observation of Physical Behavior},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24072359}
}
Kostenlos starten →