Automated Ecological Assessment of Physical Activity: Advancing Direct Observation
Technological advances provide opportunities for automating direct observations of physical activity, which allow for continuous monitoring and feedback. This pilot study evaluated the initial validity of computer vision algorithms for ecological assessment of physical activity. The sample comprised...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-12-01
|
Series: | International Journal of Environmental Research and Public Health |
Subjects: | |
Online Access: | https://www.mdpi.com/1660-4601/14/12/1487 |
id |
doaj-357072162ae04b128df5b9f2d31b998f |
---|---|
record_format |
Article |
spelling |
doaj-357072162ae04b128df5b9f2d31b998f2020-11-24T20:48:26ZengMDPI AGInternational Journal of Environmental Research and Public Health1660-46012017-12-011412148710.3390/ijerph14121487ijerph14121487Automated Ecological Assessment of Physical Activity: Advancing Direct ObservationJordan A. Carlson0Bo Liu1James F. Sallis2Jacqueline Kerr3J. Aaron Hipp4Vincent S. Staggs5Amy Papa6Kelsey Dean7Nuno M. Vasconcelos8Department of Pediatrics, Children’s Mercy Kansas City, Kansas City, MO 64108, USADepartment of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USADepartment of Family Medicine and Public Health, University of California San Diego, La Jolla, CA 92093, USADepartment of Family Medicine and Public Health, University of California San Diego, La Jolla, CA 92093, USADepartment of Parks, Recreation and Tourism Management, North Carolina State University, Raleigh, NC 27695, USADepartment of Pediatrics, Children’s Mercy Kansas City, Kansas City, MO 64108, USADepartment of Pediatrics, Children’s Mercy Kansas City, Kansas City, MO 64108, USADepartment of Pediatrics, Children’s Mercy Kansas City, Kansas City, MO 64108, USADepartment of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USATechnological advances provide opportunities for automating direct observations of physical activity, which allow for continuous monitoring and feedback. This pilot study evaluated the initial validity of computer vision algorithms for ecological assessment of physical activity. The sample comprised 6630 seconds per camera (three cameras in total) of video capturing up to nine participants engaged in sitting, standing, walking, and jogging in an open outdoor space while wearing accelerometers. Computer vision algorithms were developed to assess the number and proportion of people in sedentary, light, moderate, and vigorous activity, and group-based metabolic equivalents of tasks (MET)-minutes. Means and standard deviations (SD) of bias/difference values, and intraclass correlation coefficients (ICC) assessed the criterion validity compared to accelerometry separately for each camera. The number and proportion of participants sedentary and in moderate-to-vigorous physical activity (MVPA) had small biases (within 20% of the criterion mean) and the ICCs were excellent (0.82–0.98). Total MET-minutes were slightly underestimated by 9.3–17.1% and the ICCs were good (0.68–0.79). The standard deviations of the bias estimates were moderate-to-large relative to the means. The computer vision algorithms appeared to have acceptable sample-level validity (i.e., across a sample of time intervals) and are promising for automated ecological assessment of activity in open outdoor settings, but further development and testing is needed before such tools can be used in a diverse range of settings.https://www.mdpi.com/1660-4601/14/12/1487accelerometryexercisemeasurementparkspublic health |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jordan A. Carlson Bo Liu James F. Sallis Jacqueline Kerr J. Aaron Hipp Vincent S. Staggs Amy Papa Kelsey Dean Nuno M. Vasconcelos |
spellingShingle |
Jordan A. Carlson Bo Liu James F. Sallis Jacqueline Kerr J. Aaron Hipp Vincent S. Staggs Amy Papa Kelsey Dean Nuno M. Vasconcelos Automated Ecological Assessment of Physical Activity: Advancing Direct Observation International Journal of Environmental Research and Public Health accelerometry exercise measurement parks public health |
author_facet |
Jordan A. Carlson Bo Liu James F. Sallis Jacqueline Kerr J. Aaron Hipp Vincent S. Staggs Amy Papa Kelsey Dean Nuno M. Vasconcelos |
author_sort |
Jordan A. Carlson |
title |
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation |
title_short |
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation |
title_full |
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation |
title_fullStr |
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation |
title_full_unstemmed |
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation |
title_sort |
automated ecological assessment of physical activity: advancing direct observation |
publisher |
MDPI AG |
series |
International Journal of Environmental Research and Public Health |
issn |
1660-4601 |
publishDate |
2017-12-01 |
description |
Technological advances provide opportunities for automating direct observations of physical activity, which allow for continuous monitoring and feedback. This pilot study evaluated the initial validity of computer vision algorithms for ecological assessment of physical activity. The sample comprised 6630 seconds per camera (three cameras in total) of video capturing up to nine participants engaged in sitting, standing, walking, and jogging in an open outdoor space while wearing accelerometers. Computer vision algorithms were developed to assess the number and proportion of people in sedentary, light, moderate, and vigorous activity, and group-based metabolic equivalents of tasks (MET)-minutes. Means and standard deviations (SD) of bias/difference values, and intraclass correlation coefficients (ICC) assessed the criterion validity compared to accelerometry separately for each camera. The number and proportion of participants sedentary and in moderate-to-vigorous physical activity (MVPA) had small biases (within 20% of the criterion mean) and the ICCs were excellent (0.82–0.98). Total MET-minutes were slightly underestimated by 9.3–17.1% and the ICCs were good (0.68–0.79). The standard deviations of the bias estimates were moderate-to-large relative to the means. The computer vision algorithms appeared to have acceptable sample-level validity (i.e., across a sample of time intervals) and are promising for automated ecological assessment of activity in open outdoor settings, but further development and testing is needed before such tools can be used in a diverse range of settings. |
topic |
accelerometry exercise measurement parks public health |
url |
https://www.mdpi.com/1660-4601/14/12/1487 |
work_keys_str_mv |
AT jordanacarlson automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT boliu automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT jamesfsallis automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT jacquelinekerr automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT jaaronhipp automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT vincentsstaggs automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT amypapa automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT kelseydean automatedecologicalassessmentofphysicalactivityadvancingdirectobservation AT nunomvasconcelos automatedecologicalassessmentofphysicalactivityadvancingdirectobservation |
_version_ |
1716807760155246592 |