Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera
Abstract
:1. Introduction
2. Materials and Methods
2.1. Sample
2.2. Play Session Protocol
2.3. Measures
2.3.1. Sociodemographic Characteristics
2.3.2. Anthropometric Measurements
2.3.3. Physical Activity
Microsoft’s Kinect
Image Acquisition
Image Processing
Video Tracking
Fourier Motion Analysis
Triaxial Accelerations
Children’s Activity Rating Scale (CARS)
2.4. Statistical Analyses
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Ekelund, U.; Luan, J.; Sherar, L.B.; Esliger, D.W.; Griew, P.; Cooper, A. Moderate to vigorous physical activity and sedentary time and cardiometabolic risk factors in children and adolescents. JAMA 2012, 307, 704–712. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Janz, K.F.; Letuchy, E.M.; Eichenberger Gilmore, J.M.; Burns, T.L.; Torner, J.C.; Willing, M.C.; Levy, S.M. Early physical activity provides sustained bone health benefits later in childhood. Med. Sci. Sports Exerc. 2010, 42, 1072–1078. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- McCullough, A.K.; Duch, H.; Garber, C.E. Interactive Dyadic Physical Activity and Spatial Proximity Patterns in 2-Year-Olds and Their Parents. Children 2018, 5, 167. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Uijtdewilligen, L.; Brown, H.E.; Müller-Riemenschneider, F.; Lim, Y.W.; Brage, S.; van Sluijs, E.M. A systematic review of methods to measure family co-participation in physical activity. Obes. Rev. 2017, 18, 1454–1472. [Google Scholar] [CrossRef] [PubMed]
- Knuth, A.G.; Silva, I.C.M.; van Hees, V.T.; Cordeira, K.; Matijasevich, A.; Barros, A.J.D.; Santos, I.; Ekelund, U.; Hallal, P.C. Objectively-measured physical activity in children is influenced by social indicators rather than biological lifecourse factors: Evidence from a Brazilian cohort. Prev. Med. 2017, 97, 40–44. [Google Scholar] [CrossRef] [PubMed]
- Carlson, J.A.; Liu, B.; Sallis, J.F.; Kerr, J.; Hipp, J.A.; Staggs, V.S.; Papa, A.; Dean, K.; Vasconcelos, N.M. Automated ecological assessment of physical activity: Advancing direct observation. Int. J. Environ. Res. Public Health 2017, 14, 1487. [Google Scholar] [CrossRef] [Green Version]
- Han, J.; Shao, L.; Xu, D.; Shotton, J. Enhanced Computer Vision With Microsoft Kinect Sensor: A Review. IEEE Trans. Cybern. 2013, 43, 1318–1334. [Google Scholar]
- Silva, P.; Santiago, C.; Reis, L.P.; Sousa, A.; Mota, J.; Welk, G. Assessing physical activity intensity by video analysis. Physiol. Meas. 2015, 36, 1037–1046. [Google Scholar] [CrossRef] [Green Version]
- Maile, S.; Kobel, S.; Munz, M.; Engleder, T.; Steinacker, J.M.; Capanni, F. 3D-based visual physical activity assessment of children. Curr. Dir. Biomed. Eng. 2015, 1, 462–465. [Google Scholar] [CrossRef]
- Rosenberg, M.; Thornton, A.L.; Lay, B.S.; Ward, B.; Nathan, D.; Hunt, D.; Braham, R. Development of a kinect software tool to classify movements during active video gaming. PLoS ONE 2016, 11, e0159356. [Google Scholar] [CrossRef]
- Koporec, G.; Vučković, G.; Milić, R.; Perš, J. Quantitative contact-less estimation of energy expenditure from video and 3D imagery. Sensors 2018, 18, 2435. [Google Scholar] [CrossRef] [Green Version]
- Hõrak, H. Computer vision-based unobtrusive physical activity monitoring in school by room-level physical activity estimation: A method proposition. Information 2019, 10, 269. [Google Scholar] [CrossRef] [Green Version]
- Rowland, T. Children’s Exercise Physiology; Human Kinetics: Champaign, IL, USA, 2005. [Google Scholar]
- Centers for Disease Control and Prevention. Anthropometric Reference Data for Children and Adults: United States 2007–2010. Available online: https://www.ncbi.nlm.nih.gov/pubmed/25204692 (accessed on 23 December 2019).
- Stone, E.E.; Skubic, M. Unobtrusive, continuous, in-home gait measurement using the microsoft kinect. IEEE Trans. Biomed. Eng. 2013, 60, 2925–2932. [Google Scholar] [CrossRef] [PubMed]
- John, D.; Sasaki, J.; Staudenmayer, J.; Mavilia, M.; Freedson, P.S. Comparison of raw acceleration from the genea and actigraphTM GT3X+ activity monitors. Sensors 2013, 13, 14754–14763. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Gonzalez, R.; Woods, R. Digital Image Processing, 3rd ed.; Pearson: Up Saddle River, NJ, USA, 2008. [Google Scholar]
- Loumponias, K.; Vretos, N.; Daras, P.; Tsaklidis, G. Using Kalman Filter and Tobit Kalman Filter in Order To Improve the Motion Recorded By Kinect Sensor II. In Proceedings of the 29th Panhellenic Statistics Conference, Naussa, Bahamas, 4–7 May 2016; pp. 322–334. [Google Scholar]
- Meriam, J.; Kraige, L. Engineering Mechanics-Dynamics, 7th ed.; John Wiley & Sons: Hoboken, NJ, USA, 2012; ISBN 0027-8424. [Google Scholar]
- Puhl, J.; Greaves, K.; Hoyt, M. Children’s activity rating scale (Cars): Description and calibration. Res. Q. Exerc. Sport 1990, 61, 26–36. [Google Scholar] [CrossRef] [PubMed]
- Van Cauwenberghe, E.; Labarque, V.; Trost, S.G.; De Bourdeaudhuij, I.; Cardon, G. Calibration and comparison of accelerometer cut points in preschool children. Int. J. Pediatr. Obes. 2011, 6, 582–590. [Google Scholar] [CrossRef] [PubMed]
- Trost, S.G.; Fees, B.S.; Haar, S.J.; Murray, A.D.; Crowe, L.K. Identification and validity of accelerometer cut-points for toddlers. Obesity 2012, 20, 2317–2319. [Google Scholar] [CrossRef]
- Breiman, L. Classification and Regression Trees; Routledge: New York, NY, USA, 1984. [Google Scholar]
- Meier, U. Nonparametric equivalence testing with respect to the median difference. Pharm. Stat. 2010, 9, 142–150. [Google Scholar] [CrossRef]
- Bai, J.; Di, C.; Xiao, L.; Evenson, K.R.; LaCroix, A.Z.; Crainiceanu, C.M.; Buchner, D.M. An activity index for raw accelerometry data and its comparison with other activity metrics. PLoS ONE 2016, 11, e0160644. [Google Scholar] [CrossRef] [Green Version]
- Kerr, J.; Carlson, J.; Godbole, S.; Cadmus-Bertram, L.; Bellettiere, J.; Hartman, S. Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods. Med. Sci. Sports Exerc. 2018, 50, 1518–1524. [Google Scholar] [CrossRef]
- Tremblay, M.S.; Aubert, S.; Barnes, J.D.; Saunders, T.J.; Carson, V.; Latimer-Cheung, A.E.; Chastin, S.F.M.; Altenburg, T.M.; Chinapaw, M.J.M.; Aminian, S.; et al. Sedentary Behavior Research Network (SBRN)—Terminology Consensus Project process and outcome. Int. J. Behav. Nutr. Phys. Act. 2017, 14, 1–17. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Conger, S.A.; Guo, J.; Fulkerson, S.M.; Pedigo, L.; Chen, H.; Bassett, D.R.J. Objective Assessment of Strength Training Exercises using a Wrist-Worn Accelerometer. Med. Sci. Sports Exerc. 2016, 48, 1847–1855. [Google Scholar] [CrossRef] [PubMed]
- Arivazhagan, S.; Shebiah, R.N.; Harini, R.; Swetha, S. Human action recognition from RGB-D data using complete local binary pattern. Cogn. Syst. Res. 2019, 58, 94–104. [Google Scholar] [CrossRef]
- Zhang, H.B.; Zhang, Y.X.; Zhong, B.; Lei, Q.; Yang, L.; Du, J.X.; Chen, D.S. A comprehensive survey of vision-based human action recognition methods. Sensors 2019, 19, 1005. [Google Scholar] [CrossRef] [Green Version]
- Ghaderi, Z.; Khotanlou, H. Weakly supervised pairwise Frank–Wolfe algorithm to recognize a sequence of human actions in RGB-D videos. Signal Image Video Process. 2019, 13, 1619–1627. [Google Scholar] [CrossRef]
- Standley, T.; Sener, O.; Chen, D.; Savarese, S. image2mass: Estimating the Mass of an Object from Its Image. In Proceedings of the 1st Annual Conference on Robot Learning; Levine, S., Vanhoucke, V., Goldberg, K., Eds.; PMLR: Mountain View, CA, USA, 2017; Volume 78, pp. 324–333. [Google Scholar]
- Sirard, J.R.; Trost, S.G.; Pfeiffer, K.A.; Dowda, M.; Pate, R.R. Calibration and evaluation of an objective measure of physical activity in preschool children. J. Phys. Act. Health 2005, 2, 345–357. [Google Scholar] [CrossRef] [Green Version]
- Banda, J.A.; Haydel, K.F.; Davila, T.; Desai, M.; Bryson, S.; Haskell, W.L.; Matheson, D.; Robinson, T.N. Effects of varying epoch lengths, wear time algorithms, and activity cut-points on estimates of child sedentary behavior and physical activity from accelerometer data. PLoS ONE 2016, 11, e0150534. [Google Scholar] [CrossRef] [Green Version]
Median (IQR) | AUC (95% C.I.) | Sensitivity | Specificity | Median Difference (90% CI) | p-Value | ||
---|---|---|---|---|---|---|---|
Δ = 10% | Δ = 20% | ||||||
SED (% time) | |||||||
DO | 25 (20)% | ||||||
CART | 33 (27)% | 0.89 (0.87, 0.91) | 81% | 81% | 14 (−2, 19)% | >0.05 | 0.01 |
MCART | 36 (24)% | 0.85 (0.84, 0.89) | 80% | 76% | 16 (5, 22)% | >0.05 | >0.05 |
LPA (% time) | |||||||
DO | 37 (28)% | ||||||
CART | 29 (13)% | 0.87 (0.85, 0.90) | 66% | 90% | −8 (−17, 0)% | >0.05 | 0.005 |
MCART | 40 (10)% | 0.83 (0.78, 0.86) | 66% | 81% | −4 (−12, 10)% | >0.05 | 0.02 |
MVPA (% time) | |||||||
DO | 28 (18)% | ||||||
CART | 24 (15)% | 0.92 (0.89, 0.93) | 71% | 95% | −5 (−7, −2)% | 0.02 | <0.001 |
MCART | 25 (17)% | 0.88 (0.84, 0.90) | 64% | 92% | −3 (−9, 0)% | 0.01 | <0.001 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
McCullough, A.K.; Rodriguez, M.; Garber, C.E. Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera. Sensors 2020, 20, 1141. https://doi.org/10.3390/s20041141
McCullough AK, Rodriguez M, Garber CE. Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera. Sensors. 2020; 20(4):1141. https://doi.org/10.3390/s20041141
Chicago/Turabian StyleMcCullough, Aston K., Melanie Rodriguez, and Carol Ewing Garber. 2020. "Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera" Sensors 20, no. 4: 1141. https://doi.org/10.3390/s20041141