Hierarchical Classification of Low Resolution Thermal Images for Occupancy Estimation

Liam Walmsley-Eyre, Rachel Cardell-Oliver

Research output: Chapter in Book/Conference paperConference paper

4 Citations (Scopus)

Abstract

Occupancy estimators (sensors which can accurately estimate the number of people occupying a space) hold great potential for reducing the power usage of lighting and heating, ventilation, and air conditioning (HVAC) systems. In this paper we use low-resolution thermal sensors for occupancy estimation, due to their high temporal and spatial resolution and low invasiveness. We extend the connected component analysis and frame-classification approach taken in prior work with several new features designed to provide interesting information about the frame and components, and also examine an alternative approach that classifies the connected components individually. This is done by creating a prototype system used to collect and label data from scenes. We found that the new features significantly improve accuracy, but that the connected component classification approach is no better than frame classification for typical scenes with few occupants. In scenes with many or close occupants, We found that connected component classification produced more accurate predictions.

Original languageEnglish
Title of host publicationProceedings: 2017 IEEE 42nd Conference on Local Computer Networks Workshops LCN Workshops 2017
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages9-17
Number of pages9
ISBN (Electronic)9781509065837
DOIs
Publication statusPublished - 14 Nov 2017
Event42nd IEEE Conference on Local Computer Networks Workshops, LCN Workshops 2017 - Singapore, Singapore
Duration: 9 Oct 201712 Oct 2017

Conference

Conference42nd IEEE Conference on Local Computer Networks Workshops, LCN Workshops 2017
CountrySingapore
CitySingapore
Period9/10/1712/10/17

Fingerprint Dive into the research topics of 'Hierarchical Classification of Low Resolution Thermal Images for Occupancy Estimation'. Together they form a unique fingerprint.

Cite this