Low-Resolution Overhead Thermal Tripwire for Occupancy Estimation

Mertcan Cokbas, Prakash Ishwar, Janusz Konrad; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 88-89

Abstract


Smart buildings use people counts for various tasks ranging from energy-efficient HVAC and lighting to space-utilization analysis and emergency-response. We propose a people counting system which uses a low-resolution thermal sensor. Unlike previous thermal sensor based people counting systems, we use an overhead tripwire configuration at entryways to detect and track transient entries or exits. We develop two people counting algorithms for this system configuration. To evaluate our algorithms we have collected and labeled a low-resolution thermal video dataset with the proposed system configuration. The dataset, which is the largest of its kind, will be published alongside the paper. We also propose new evaluation metrics that are more suitable for systems that are subject to drift and jitter.

Related Material


[pdf]
[bibtex]
@InProceedings{Cokbas_2020_CVPR_Workshops,
author = {Cokbas, Mertcan and Ishwar, Prakash and Konrad, Janusz},
title = {Low-Resolution Overhead Thermal Tripwire for Occupancy Estimation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}