As sedentary lifestyles and childhood obesity are becoming more prevalent, research in the field of physical activity (PA) has gained much momentum. Monitoring the PA of children and adolescents is crucial for ascertaining and understanding the phenomena that facilitate and hinder PA in order to develop effective interventions for promoting physically active habits. Popular individual-level measures are sensitive to social desirability bias and subject reactivity. Intrusiveness of these methods, especially when studying children, also limits the possible duration of monitoring and assumes strict submission to human research ethics requirements and vigilance in personal data protection. Meanwhile, growth in computational capacity has enabled computer vision researchers to successfully use deep learning algorithms for real-time behaviour analysis such as action recognition. This work analyzes the weaknesses of existing methods used in PA research; gives an overview of relevant advances in video-based action recognition methods; and proposes the outline of a novel action intensity classifier utilizing sensor-supervised learning for estimating ambient PA. The proposed method, if applied as a distributed privacy-preserving sensor system, is argued to be useful for monitoring the spatio-temporal distribution of PA in schools over long periods and assessing the efficiency of school-based PA interventions.

No abstract

No abstract

This work presents an inductive search of physical activity intensity features for developing computer vision data sets used in automatic physical activity observation systems. An online survey was conducted to calibrate the ground truth definitions in a data set of video synchronized with accelerometers. Experts from the research field were asked to classify 24 short video samples of children's physical activity relative to three metabolic equivalence of task units -the presumed threshold of moderate to vigorous physical activity. Leave-one-out disagreement analysis was applied until moderate agreement was achieved (12 respondents remain, Light's κ = 0.62). The predictive power of features from hip-worn ActiGraph wGT3X-BT 30Hz raw accelerations and several freely available 2D pose estimation models are explored by cut-point analyses and logistic regression while using several approaches to account for uncertainty. Features from the acceleration-and video pose estimation domains are combined in correlation analyses in a twelve-hour data set representing relatively unstructured behavior from 24 children ages 8-13 filmed in four different locations. Results indicate that changes in the hip angles of pose-estimated kinematic skeletons across 10 fps video frames can supplement or possibly substitute accelerometers for estimating physical activity intensity in uncrowded indoor scenes. When taking such an approach to labeling physical activity recognition data sets, good joint tracking capacity of the pose estimation method should increase the robustness of the hip angle features.INDEX TERMS 2D pose estimation, ActiGraph, knowledge engineering, moderate to vigorous physical activity, smart cameras.RAIN ERIC HAAMER (Member, IEEE) was born in Tartu, Estonia, in 1994. He received the B.Sc. degree in computer engineering and the M.S. degree in computer engineering and robotics from the University of Tartu, Estonia, in 2017 and 2019, respectively.Since 2017, he has been a Senior Engineer and a Virtual Reality Specialist at the iCV, Institute of Technology, University of Tartu. He is currently working as a Specialist with the iCV, Tartu University. His research interests include audio, image and video processing, virtual, augmented and mixed reality, embedded systems, and machine learning.