Automated Ecological Assessment of Physical Activity: Advancing Direct Observation.
Automated Ecological Assessment of Physical Activity: Advancing Direct Observation.
复制标题
DOI：
10.3390/ijerph14121487
复制
发表时间：
2017-12-01
影响因子：
--
通讯作者：
Vasconcelos NM
中科院分区：
文献类型：
--
作者：
Carlson JA;Liu B;Sallis JF;Kerr J;Hipp JA;Staggs VS;Papa A;Dean K;Vasconcelos NM
技术进步为自动化直接观察体力活动提供了机会，从而允许持续监测和反馈。这项初步研究评估了计算机视觉算法用于生态体力活动评估的初步有效性。样本包括每个摄像头(总共三个摄像头)6630秒的视频，捕捉到多达9名参与者戴着加速计在户外空间坐、站、走和慢跑。计算机视觉算法被开发来评估久坐、轻度、中度和剧烈活动以及基于组的代谢量任务(MET)分钟的人数和比例。偏差/差值的平均值和标准差(SD)以及组内相关系数(ICC)分别评估了标准的有效性，并与加速度法进行了比较。久坐和中等到剧烈体力活动(MVPA)的参与者的数量和比例有很小的偏差(在标准均值的20%以内)，ICC很好(0.82-0.98)。总表分钟数被轻微低估9.3-17.1%，ICC良好(0.68-0.79)。相对于平均值，偏差估计的标准偏差是中等到很大的。计算机视觉算法似乎具有可接受的样本级有效性(即，在时间间隔的样本上)，并有望对户外开放环境中的活动进行自动生态评估，但在这些工具可以在各种环境中使用之前，还需要进一步的开发和测试。
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.
登录
查看更多内容
DOI：
10.1097/00005768-199805000-00021
发表时间：
1998-05-01
期刊：
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE
影响因子：
--
作者：
Freedson, PS;Melanson, E;Sirard, J
通讯作者：
Sirard, J
DOI：
10.1198/016214502753479392
发表时间：
2002-03-01
影响因子：
3.7
作者：
Lin, L;Hedayat, AS;Yang, M
通讯作者：
Yang, M
DOI：
10.1007/978-3-319-40902-3_26
发表时间：
2017-01-01
期刊：
SEEING CITIES THROUGH BIG DATA: RESEARCH, METHODS AND APPLICATIONS IN URBAN INFORMATICS
影响因子：
--
作者：
Hipp, J. Aaron;Adlakha, Deepti;Pless, Robert
通讯作者：
Pless, Robert
影响因子：
3.1
作者：
Cohen, Deborah A.;Han, Bing;Bhatia, Rajiv
通讯作者：
Bhatia, Rajiv
影响因子：
1.9
作者：
LANDIS, JR;KOCH, GG
通讯作者：
KOCH, GG