Paper Info
Title
People detection and tracking from aerial thermal views
Abstract
Detection and tracking of people in visible-light images has been subject to extensive research in the past decades with applications ranging from surveillance to search-and-rescue. Following the growing availability of thermal cameras and the distinctive thermal signature of humans, research effort has been focusing on developing people detection and tracking methodologies applicable to this sensing modality. However, a plethora of challenges arise on the transition from visible-light to thermal images, especially with the recent trend of employing thermal cameras onboard aerial platforms (e.g. in search-and-rescue research) capturing oblique views of the scenery. This paper presents a new, publicly available dataset of annotated thermal image sequences, posing a multitude of challenges for people detection and tracking. Moreover, we propose a new particle filter based framework for tracking people in aerial thermal images. Finally, we evaluate the performance of this pipeline on our dataset, incorporating a selection of relevant, state-of-the-art methods and present a comprehensive discussion of the merits spawning from our study.
Year
DOI
Venue
2014
10.1109/ICRA.2014.6907094
Robotics and Automation
Keywords
DocType
Volume
cameras,image sensors,image sequences,infrared imaging,object detection,object tracking,particle filtering (numerical methods),video surveillance,aerial thermal view,availability,distinctive thermal signature,particle filter,people detection methodology,people tracking methodology,performance evaluation,search-and-rescue research,sensing modality,surveillance,thermal camera,thermal image sequence,visible-light imaging
Conference
2014
Issue
ISSN
Citations 
1
1050-4729
37
PageRank 
References 
Authors
1.39
12
4
Name
Order
Citations
PageRank
Portmann, J.1371.39
Simon Lynen261726.48
Margarita Chli3128353.59
Roland Siegwart47640551.49