Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Generating Object Proposals for Vehicle Detection in Aerial Images

: Sommer, L.

Postprint urn:nbn:de:0011-n-4618292 (2.3 MByte PDF)
MD5 Fingerprint: 326122c8a4caacef3d9d3c3659e2dd15
Created on: 24.8.2017

Beyerer, Jürgen (Ed.); Pak, Alexey (Ed.):
Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory 2016. Proceedings : Triberg-Nussbach, July, 24 to 29, 2016
Karlsruhe: KIT Scientific Publishing, 2017 (Karlsruher Schriften zur Anthropomatik 33)
ISBN: 978-3-7315-0678-2
DOI: 10.5445/KSP/1000070009
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2016, Triberg-Nussbach>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Vehicle detection in aerial images is an important task in many
applications such as screening of large areas or traffic monitoring. In general, classifiers or a cascade of classifiers within a sliding window approach are used to perform vehicle detection. However, sliding window approaches are limited for vehicle detection in a real-time system due to the huge number of windows to classify. To overcome this challenge, several objects proposals methods have been proposed for generating candidate windows
in detection frameworks. Impressive results have been achieved on common
detection benchmark datasets like Pascal VOC 2007 for a significantly
reduced number of candidate windows. However, these datasets, which are
used to develop the object proposals methods, exhibit considerably differing
characteristics compared to aerial images. In this report, we examine
the applicability of such object proposals methods for vehicle detection in
aerial images. Therefore, we evaluate the performance of seven state-ofthe-art
object proposals methods on the publicly available DLR 3K Munich Vehicle Aerial Image Dataset. Relevant adaptions are highlighted by using the Selective Search method. Finally, the adapted methods are compared to baseline approaches like sliding window.