Evaluation of the Fusion of Visible and Thermal Image Data for People Detection with a Trained People Detector

Achim Königs, Dirk Schulz

2013

Abstract

People detection surely is one of the hottest topics in Computer Vision. In this work we propose and evaluate the fusion of thermal images and images from the visible spectrum for the task of people detection. Our main goal is to reduce the false positive rate of the Implicit Shape Model (ISM) object detector, which is commonly used for people detection. We describe five possible methods to integrate the thermal data into the detection process at different processing steps. Those five methods are evaluated on several test sets we recorded. Their performance is compared to three baseline detection approaches. The test sets contain data from an indoor environment and from outdoor environments at days with different ambient temperatures. The data fusion methods decrease the false positive rate especially on the outdoor test sets.

Paper Citation

in Harvard Style

Königs A. and Schulz D. (2013). Evaluation of the Fusion of Visible and Thermal Image Data for People Detection with a Trained People Detector . In Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-71-6, pages 345-352. DOI: 10.5220/0004484203450352

in Bibtex Style

@conference{icinco13,
author={Achim Königs and Dirk Schulz},
title={Evaluation of the Fusion of Visible and Thermal Image Data for People Detection with a Trained People Detector},
booktitle={Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2013},
pages={345-352},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004484203450352},
isbn={978-989-8565-71-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Evaluation of the Fusion of Visible and Thermal Image Data for People Detection with a Trained People Detector
SN - 978-989-8565-71-6
AU - Königs A.
AU - Schulz D.
PY - 2013
SP - 345
EP - 352
DO - 10.5220/0004484203450352