Jordan A Carlson, B O Liu1, James F Sallis2, J Aaron Hipp3, Vincent S Staggs, Jacqueline Kerr2, Amy Papa4, Kelsey Dean4, Nuno M Vasconcelos1. 1. Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA. 2. Department of Family Medicine and Public Health, University of California San Diego, La Jolla, CA. 3. Department of Parks, Recreation, and Tourism Management and Center for Geospatial Analytics, North Carolina State University, Raleigh, NC. 4. Center for Children's Healthy Lifestyles and Nutrition, Children's Mercy Hospital, Kansas City, MO.
Abstract
PURPOSE: To test the validity of the Ecological Video Identification of Physical Activity (EVIP) computer vision algorithms for automated video-based ecological assessment of physical activity in settings such as parks and schoolyards. METHODS: Twenty-seven hours of video were collected from stationary overhead video cameras across 22 visits in nine sites capturing organized activities. Each person in the setting wore an accelerometer, and each second was classified as moderate-to-vigorous physical activity or sedentary/light activity. Data with 57,987 s were used to train and test computer vision algorithms for estimating the total number of people in the video and number of people active (in moderate-to-vigorous physical activity) each second. In the testing data set (38,658 s), video-based System for Observing Play and Recreation in Communities (SOPARC) observations were conducted every 5 min (130 observations). Concordance correlation coefficients (CCC) and mean absolute errors (MAE) assessed agreement between (1) EVIP and ground truth (people counts+accelerometry) and (2) SOPARC observation and ground truth. Site and scene-level correlates of error were investigated. RESULTS: Agreement between EVIP and ground truth was high for number of people in the scene (CCC = 0.88; MAE = 2.70) and moderate for number of people active (CCC = 0.55; MAE = 2.57). The EVIP error was uncorrelated with camera placement, presence of obstructions or shadows, and setting type. For both number in scene and number active, EVIP outperformed SOPARC observations in estimating ground truth values (CCC were larger by 0.11-0.12 and MAE smaller by 41%-48%). CONCLUSIONS: Computer vision algorithms are promising for automated assessment of setting-based physical activity. Such tools would require less manpower than human observation, produce more and potentially more accurate data, and allow for ongoing monitoring and feedback to inform interventions.
PURPOSE: To test the validity of the Ecological Video Identification of Physical Activity (EVIP) computer vision algorithms for automated video-based ecological assessment of physical activity in settings such as parks and schoolyards. METHODS: Twenty-seven hours of video were collected from stationary overhead video cameras across 22 visits in nine sites capturing organized activities. Each person in the setting wore an accelerometer, and each second was classified as moderate-to-vigorous physical activity or sedentary/light activity. Data with 57,987 s were used to train and test computer vision algorithms for estimating the total number of people in the video and number of people active (in moderate-to-vigorous physical activity) each second. In the testing data set (38,658 s), video-based System for Observing Play and Recreation in Communities (SOPARC) observations were conducted every 5 min (130 observations). Concordance correlation coefficients (CCC) and mean absolute errors (MAE) assessed agreement between (1) EVIP and ground truth (people counts+accelerometry) and (2) SOPARC observation and ground truth. Site and scene-level correlates of error were investigated. RESULTS: Agreement between EVIP and ground truth was high for number of people in the scene (CCC = 0.88; MAE = 2.70) and moderate for number of people active (CCC = 0.55; MAE = 2.57). The EVIP error was uncorrelated with camera placement, presence of obstructions or shadows, and setting type. For both number in scene and number active, EVIP outperformed SOPARC observations in estimating ground truth values (CCC were larger by 0.11-0.12 and MAE smaller by 41%-48%). CONCLUSIONS: Computer vision algorithms are promising for automated assessment of setting-based physical activity. Such tools would require less manpower than human observation, produce more and potentially more accurate data, and allow for ongoing monitoring and feedback to inform interventions.
Authors: Jenna L Hollis; Amanda J Williams; Rachel Sutherland; Elizabeth Campbell; Nicole Nathan; Luke Wolfenden; Philip J Morgan; David R Lubans; John Wiggers Journal: Prev Med Date: 2015-11-22 Impact factor: 4.018
Authors: Deborah A Cohen; Bing Han; Jennifer Isacoff; Bianca Shulaker; Stephanie Williamson; Terry Marsh; Thomas L McKenzie; Megan Weir; Rajiv Bhatia Journal: J Phys Act Health Date: 2014-06-20
Authors: Deborah A Cohen; Claude Setodji; Kelly R Evenson; Phillip Ward; Sandra Lapham; Amy Hillier; Thomas L McKenzie Journal: J Phys Act Health Date: 2011-11
Authors: Robert G Weaver; Aaron Beighle; Heather Erwin; Michelle Whitfield; Michael W Beets; James W Hardin Journal: J Phys Act Health Date: 2018-05-10
Authors: Deborah A Cohen; Bing Han; Catherine J Nagel; Peter Harnik; Thomas L McKenzie; Kelly R Evenson; Terry Marsh; Stephanie Williamson; Christine Vaughan; Sweatha Katta Journal: Am J Prev Med Date: 2016-05-18 Impact factor: 5.043
Authors: Inbal Nahum-Shani; Shawna N Smith; Bonnie J Spring; Linda M Collins; Katie Witkiewitz; Ambuj Tewari; Susan A Murphy Journal: Ann Behav Med Date: 2018-05-18
Authors: Jordan A Carlson; Bo Liu; James F Sallis; Jacqueline Kerr; J Aaron Hipp; Vincent S Staggs; Amy Papa; Kelsey Dean; Nuno M Vasconcelos Journal: Int J Environ Res Public Health Date: 2017-12-01 Impact factor: 3.390