Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Robust detection of moving vehicles in wide area motion imagery

: Teutsch, Michael; Grinberg, Michael


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. Proceedings : 26 June - 1 July 2016 Las Vegas, Nevada
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2016
ISBN: 978-1-5090-1438-5 (Print)
ISBN: 978-1-4673-8850-4
ISBN: 978-1-5090-1437-8 (Online)
Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) <29, 2016, Las Vegas/Nev.>
Workshop "Moving Cameras Meet Video Surveillance - From Body-Borne Cameras to Drones" <2016, Las Vegas/Nev.>
Conference Paper
Fraunhofer IOSB ()

Multiple object tracking in Wide Area Motion Imagery (WAMI) data is usually based on initial detections coming from background subtraction or frame differencing. However, these methods are prone to produce split and merged detections. Appearance based vehicle detection can be an alternative but is not well-suited for WAMI data since classifier models are of weak discriminative power for vehicles in top view at low resolution. We introduce a moving vehicle detection algorithm that combines 2-frame differencing with a vehicle appearance model to improve object detection. Our main contributions are (1) integration of robust vehicle detection with split/merge handling and (2) estimation of assignment likelihoods between object hypotheses in consecutive frames using an appearance based similarity measure. Without using any prior knowledge, we achieve state-of-the-art detection rates and produce tracklets that considerably simplify the data association problem for multiple object tracking.