Fusion of Different Height Pyroelectric Infrared Sensors for Person Identification

Abstract

Due to the instability and poor identification ability of a single pyroelectric infrared (PIR) detector for human target identification, this paper presents a PIR detection identification system that can collect thermal infrared features from different parts of human targets through multiple PIR sensors for the human identification. First, fast Fourier transform, short-time Fourier transform, and wavelet packet transform algorithms are adopted to extract thermal infrared features of human targets. Then, the canonical correlation analysis algorithm is used to fuse different algorithm features in the feature layer. Finally, using the support vector machine to classify the human targets. In the decision-making layer, the Dempster/Shafer evidence theory is adopted to optimize the recognition results from different PIR sensors that locate at different height positions. Extensive experimental results demonstrate that the fusion of feature layer data could improve the average recognition rate of the human target with closer distance from the single sensor. In addition, the fusion of decision-making layer could improve the recognition ability of the identification system as well. When the detection distance is 6 m, the correct recognition rate of fusion system is still reached 88.75%. Compared with the system using a single sensor, the recognition rate is increased by an average of 22.67%.