🤖 AI Summary
This work addresses the challenge that individuals often struggle to accurately recall the triggers and contextual details of stressful events, which limits the efficacy of psychological interventions. To overcome this, the authors propose HeartbeatCam, a novel system that integrates physiological stress signals from consumer-grade smartwatches with open-source augmented reality (AR) glasses to create a physiology-driven, self-triggered mechanism. Upon detecting elevated stress levels, the system automatically captures sparse audiovisual contextual data. This approach enables an action-oriented method for mental health awareness, facilitating precise retrospective analysis and timely therapeutic intervention during clinical sessions. The study demonstrates the feasibility and clinical value of physiology-informed contextual logging as an auxiliary tool in mental health care.
📝 Abstract
People often recognize what triggered their stress only after the moment has passed. In therapy, this can become a recurring problem: clients are asked to remember what happened between sessions, but the details that matter (where they were, what they saw and heard, what was happening around them) are easy to lose. We introduce HeartbeatCam, a wearable sensing system that gathers contextual information during moments of elevated stress. It uses a consumer smartwatch stress signal to trigger capture from an open-source AR glasses camera, recording a sparse image-audio clip that can later be reviewed and annotated. The system adopts an actionable sensing approach to mental healthcare, using physiological signals along with contextual capture to support collaborative interpretation of stress-triggering moments with mental health professionals.