Today’s technology could contribute substantially to measuring physical activity. The current study evaluated traditional and novel approaches for assessing park use. The traditional approach involved a trained observer performing the System for Observing Play and Recreation in Communities (SOPARC) at 14 parks while wearing a point-of-view, wearable video device (WVD). The novel approach utilized computer vision to count park users in the WVD videos taken during in-person SOPARCs. Both approaches were compared to criterion counts from expert reviews of the WVD videos. In the 676 scans made during in-person SOPARCs, 293 individuals were observed while 341 were counted by experts in the corresponding WVD videos. When using scans/videos having individuals in them (84 scans/videos), intra-class correlations (ICC) indicated good-to-excellent reliability between in-person SOPARC and experts for counts of total women and men, within age groups (except seniors), of Blacks and Whites, and within intensity categories (ICCs > .87; p < 0.001). In a subsample of 42 scans/videos, 174 individuals were counted using computer vision and 213 by experts. When using 27 of the 42 WVD videos with individuals in them, ICCs indicated good reliability between computer vision and expert reviews (ICC = .83; p < 0.001). Bland-Altman analysis showed the concurrence of expert counts with both in-person SOPARC and computer vision counts decreased as the number of individuals in a scan/video increased. The results of this study support the use of a highly discrete method for obtaining point-of-view videos and the application of computer vision for automating the counting of park users in the videos.

No abstract

Evidence suggests that video captured with a wearable video device (WVD) may augment or supplant traditional methods for assessing park use. Unmanned aerial systems (UASs) are used to assess human activity, but research employing them for park assessments is sparse. Therefore, this study compared park user counts between a WVD and UAS. A diverse set of 33 amenities (e.g., playground) in three parks were videoed simultaneously by one researcher wearing a WVD and another operating the UAS. Assessments were done at 12 p.m. and 7 p.m. on weekends, with one park evaluated on two occasions 7 days apart. Two investigators independently reviewed videos and reached consensus on the counts of individuals at each amenity. Intraclass correlation coefficients (ICCs) were used to determine intra- and interrater reliabilities. A total of 404 (M = 4.7; SD = 9.6) and 389 (M = 4.5; SD = 9.0) individuals were counted in the UAS and WVD videos, respectively. Absolute agreement was 86% (74/86) and 100% when no individuals were using the amenity. Whether using all 86 videos or only videos having people (48 videos), ICCs indicated excellent reliability (ICC = .99; p < .001). The totals seen for the repeated measures were UAS = 146 and WVD = 136 for Day 1 and UAS = 169 and WVD = 161 for Day 2. Intrarater reliability was excellent for the UAS (ICC = .92; p < .001) and good for the WVD (ICC = .89; p < .001). Disagreement was mainly due to obstructions—people behind or under structures. This study provides support for the use of UASs for counting park users and future research examining the potential benefits of video analysis for assessing park use.