Power-aware action recognition with optimal sensor selection
Pasquale Panuccio, Hassan G Ghasemzadeh, Giancarlo Fortino, Roozbeh Jafari · 2011
In this paper, we present a distributed action recognition framework that minimizes power consumption of the system subject to a lower bound on the classification accuracy. The system utilizes computationally simple template matching blocks that perform classifications on individual sensor nodes. A boosting approach is employed to enhance accuracy by activating only a subset of sensors optimized in terms of power consumption and can achieve a given lower bound accuracy criterion. Our experimental results on real data shows more than 85% power saving while maintaining 80% sensitivity to detected actions.