Privacy-preserving Building Occupancy Estimation via Low-Resolution Infrared Thermal Cameras

Abstract

Building occupancy estimation has become an important topic for sustainable buildings that has attracted more attention during the pandemics. Estimating building occupancy is a considerable problem in computer vision, while computer vision has achieved breakthroughs in recent years. But, machine learning algorithms for computer vision demand large datasets that may contain users' private information to train reliable models. As privacy issues pose a severe challenge in the field of machine learning, this work aims to develop a privacy-preserved machine learning-based method for people counting using a low-resolution thermal camera with 32 by 24 pixels. The method is applicable for counting people in different scenarios, concretely, counting people in spaces smaller than the FoV of the camera, as well as large spaces over the FoV of the camera. In the first scenario, counting people in small spaces, we directly count people within the FoV of the camera by MOD techniques. Our MOD method achieves up to 56.8% mAP. In the second scenario, we use MOT techniques to track people entering and exiting the space. We record the number of people who entered and exited, and then calculate the number of people based on the tracking results. The MOT method reaches 47.4% MOTA, 78.2% MOTP, and 59.6% IDF1. Apart from the method, we create a novel thermal images dataset containing 1770 thermal images with proper annotation.