Noise-tolerant and context-aware structural vibration based activity monitoring
Amelie Bonde · 2020
Automated monitoring of humans and animals can facilitate better health and productivity. Prior monitoring approaches use video, which requires line-of-sight and high processing power, or motion detection, which has difficulty separating subtle activities. Wearable sensors can address these issues but are vulnerable to animal destructiveness and human forgetfulness. We present a system that uses structural vibration to monitor animal or human behavior. We use domain knowledge to adapt this system to different environments, and evaluate it on humans in a home office environment and on pigs at an operational pig farm.