Mechanisms for efficient integration of RSSI in localization and tracking with wireless camera networks

This paper proposes a scheme that exploits synergies between RSSI and camera measurements in object localization and tracking using Wireless Camera Networks (WCN). It is based on three main mechanisms: a training method that accurately adapts RSSI-range models to the particular environment; a sensor activation/deactivation method that balances the different information contribution and energy consumptions of camera and RSSI measurements; and a distributed Information Filter to integrate the available measurements. The joint use of these mechanisms drastically reduces energy consumption -40% with no significant degradation w.r.t. existing schemes based on only cameras and shows better robustness to target occlusions. The scheme has been implemented and validated in the indoor CONET Integrated Testbed.