Multiple walker recognition with wireless distributed pyroelectric sensors

This paper presents a wireless distributed pyroelectric sensor system, whose sensing visibilities are modulated by Frensnel lens arrays and coded masks, for multiple human walker recognition. One goal of our research is to make wireless distributed pyroelectrie sensor nodes an alternative to the centralized infrared video sensors, with lower cost, lower detectability, lower power consumption and computation, and less privacy infringement. In our previous study, we succeeded in identifying individuals walking along the same path, or just randomly inside a room, with an identification rate higher than 80% for around 10 subjects, only using one wireless sensor node. To improve the identification rate and the number of subjects that can be recognized, one-by-one or simultaneously, we employ multiple sensor nodes to, leverage the performance of the distributed sensor system. The fusion of pyroelectric biometrics from multiple nodes is performed at four different levels: sample, feature, score, and decision. The experimental results show that the proposed pyroelectric sensor system has potential to be a reliable biometric system for the verification/identification of a small group of human objects. Its applications include security monitoring, human-machine interfaces, and virtual environments. Keywords: Hidden Markov model, pyroelectric sensor, walker recognition, wireless sensor module, distributed sensor fusion