A robust system for counting people using an infrared sensor and a camera

Date
2015
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Infrared Physics and Technology
Print ISSN
1350-4495
Electronic ISSN
Publisher
Elsevier BV
Volume
72
Issue
Pages
127 - 134
Language
English
Type
Article
Journal Title
Journal ISSN
Volume Title
Series
Abstract

In this paper, a multi-modal solution to the people counting problem in a given area is described. The multi-modal system consists of a differential pyro-electric infrared (PIR) sensor and a camera. Faces in the surveillance area are detected by the camera with the aim of counting people using cascaded AdaBoost classifiers. Due to the imprecise results produced by the camera-only system, an additional differential PIR sensor is integrated to the camera. Two types of human motion: (i) entry to and exit from the surveillance area and (ii) ordinary activities in that area are distinguished by the PIR sensor using a Markovian decision algorithm. The wavelet transform of the continuous-time real-valued signal received from the PIR sensor circuit is used for feature extraction from the sensor signal. Wavelet parameters are then fed to a set of Markov models representing the two motion classes. The affiliation of a test signal is decided as the class of the model yielding higher probability. People counting results produced by the camera are then corrected by utilizing the additional information obtained from the PIR sensor signal analysis. With the proof of concept built, it is shown that the multi-modal system can reduce false alarms of the camera-only system and determines the number of people watching a TV set in a more robust manner.

Course
Other identifiers
Book Title
Keywords
Infrared sensors, Markov models, Multi-modal systems, People counting, Adaptive boosting, Cameras, Continuous time systems, Feature extraction, Infrared detectors, Infrared devices, Markov processes, Wavelet transforms, Ada boost classifiers, Decision algorithms, Markov model, Number of peoples, People counting, Wavelet parameters, Security systems
Citation
Published Version (Please cite this version)