Wireless sensor networks for activity monitoring using multi-sensor multi-modal node architecture

A multi-sensor, multi-modal sensor node for human and vehicle activity monitoring is designed and developed. As a first step to achieve our objective, we have used a dual pyroelectric IR (PIR) sensor system for human activity monitoring. The sampled data from two PIR sensors, under laboratory conditions, is first processed individually to determine the event window size, which is then fed to simple algorithms to determine direction and potentially measure speed of passing humans. We also show that human count can be obtained for some special scenarios. Preliminary results of our experimentation show the effectiveness of the simple algorithms proposed.