Understanding activity intensity in a building facility operation is important because intensity directly affects occupants' metabolic heat generation and consequently dictates heating, ventilation, and air conditioning and ventilation control demands. Existing monitoring tools rely on self-report questionnaires, metabolic equivalent measurements, wearable sensors, and basic environmental sensing. These solutions are susceptible to recall bias, lack of real-time precision, intrusive setups that alter natural behavior, and vulnerability to environmental confounding factors. Looking beyond traditional monitoring methods, researchers Moein Younesi Heravi, Inbae Jeong, and Youjin Jang explore a nonintrusive, vision-based solution that estimates physical exertion levels directly from standard video footage.
In their paper “A Vision-Based Approach for Human Activity Intensity Estimation Using Kinematic Features,” the authors address the limitations outlined above by introducing a nonintrusive Activity Intensity Score framework that extracts 2D body landmarks, groups them into kinematic chains, and computes a six-dimensional set of complementary movement parameters. These parameters are normalized and combined using a MET-referenced, data-driven weight optimization procedure to generate a unified, continuous intensity score reflecting real-time physical workload. The framework was experimentally validated using a dataset of 67 video clips from 20 participants performing low-, moderate-, and high-intensity tasks. While small in scope, this AIS method can be applied in civil engineering fields for construction ergonomics—such as fatigue-aware work-rest planning and identifying physically demanding task segments—and in building facility operations to inform adaptive HVAC and ventilation controls based on real-time occupant metabolic loads. Learn more about this study in the Journal of Computing in Civil Engineering at https://ascelibrary.org/doi/10.1061/JCCEE5.CPENG-7683. The abstract is below.
Abstract
Accurate real-time estimation of human activity intensity is essential for diverse applications such as health monitoring, ergonomics, sports science, and adaptive building management. However, existing methods often depend on intrusive wearable sensors, discrete activity classifications, or extensive training datasets, which compromise their practicality and generalizability. To address these gaps, we propose a novel activity intensity score (AIS) framework that provides a nonintrusive and continuous measure of activity intensity by analyzing video data. The proposed method applies pose estimation to video data to extract body landmarks, which are then used to compute kinematic parameters including the angular velocity, angular acceleration, range of motion, peak speed, movement frequency, and rotational energy across defined kinematic chains (e.g., arms, legs, torso). These parameters are then normalized and combined through an optimized weighted summation to produce a continuous activity intensity metric. Experimental validation was conducted with 20 participants performing various activities from low, moderate, and high intensity. Results demonstrated strong correlations between AIS scores and both activity intensity levels (Spearman’s 𝜌=0.943, 𝑝<0.001) and participants perceived exertion ratings (Pearson’s 𝑟=0.923, 𝑝<0.001). Statistical comparisons demonstrated that the AIS values effectively discriminate among these three intensity categories (Spearman’s 𝜌=0.943) and significant group differences confirmed by ANOVA (𝑝<0.001). Moreover, the AIS exhibited a strong correlation (Pearson’s 𝑟=0.923) with self-reported exertion (Borg rating of perceived exertion), indicating consistency with participants’ subjective perceptions. This occupant-invariant and domain-independent method enables robust, real-time measurement of movement intensity for applications ranging from healthcare and workplace ergonomics to sports analytics and adaptive HVAC control.
Learn more about this novel method of monitoring activity to more efficiently manage building HVAC in the ASCE Library: https://ascelibrary.org/doi/10.1061/JCCEE5.CPENG-7683.
