Measuring time spent outdoors using a wearable camera and GPS

Abstract

Numerous studies have demonstrated multiple health benefits of being outside and exposure to natural environments. It is essential to accurately measure the amount of time individuals spend outdoors to assess the impact of exposure to outdoor time on health. SenseCam is a wearable camera that automatically captures images. The annotated images provide an objective criterion for determining amount of time spent outdoors. In this paper we explored the use of SenseCam and Global Positioning System (GPS) devices to calculate time spent outdoors. We used the annotated SenseCam images to investigate the optimal threshold from the GPS data to best differentiate outdoor and indoor time. We analyzed the signal strength data recorded by the GPS with a Receiver Operating Characteristic (ROC) curve as well as a three-category logistic regression model. The ROC curve resulted in 79.4% sensitivity for indoor time and 84.1% specificity for outdoor time with an area under the curve of 0.927.