Lightweight biometric detection system for human classification using pyroelectric infrared detectors |
| |
Authors: | Burchett John Shankar Mohan Hamza A Ben Guenther Bob D Pitsianis Nikos Brady David J |
| |
Affiliation: | Fitzpatrick Center for Photonics and Communications, Duke University, Durham, North Carolina 27708, USA. johnb@ee.duke.edu |
| |
Abstract: | We use pyroelectric detectors that are differential in nature to detect motion in humans by their heat emissions. Coded Fresnel lens arrays create boundaries that help to localize humans in space as well as to classify the nature of their motion. We design and implement a low-cost biometric tracking system by using off-the-shelf components. We demonstrate two classification methods by using data gathered from sensor clusters of dual-element pyroelectric detectors with coded Fresnel lens arrays. We propose two algorithms for person identification, a more generalized spectral clustering method and a more rigorous example that uses principal component regression to perform a blind classification. |
| |
Keywords: | |
本文献已被 PubMed 等数据库收录! |
|