Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Fast deep vehicle detection in aerial images

: Sommer, L.W.; Schuchert, Tobias; Beyerer, Jürgen

Postprint urn:nbn:de:0011-n-4562350 (5.8 MByte PDF)
MD5 Fingerprint: 37f7fe7e657d5ec079aaa64c8ded9988
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 27.3.2018

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
WACV 2017, IEEE Winter Conference on Applications of Computer Vision. Proceedings : 24-31 March 2017, Santa Rosa, California
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-4822-9
ISBN: 978-1-5090-4823-6
Winter Conference on Applications of Computer Vision (WACV) <17, 2017, Santa Rosa/Calif.>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Vehicle detection in aerial images is a crucial image processing step for many applications like screening of large areas. In recent years, several deep learning based frameworks have been proposed for object detection. However, these detectors were developed for datasets that considerably differ from aerial images. In this paper, we systematically investigate the potential of Fast R-CNN and Faster R-CNN for aerial images, which achieve top performing results on common detection benchmark datasets. Therefore, the applicability of 8 state-of-the-art object proposals methods used to generate a set of candidate regions and of both detectors is examined. Relevant adaptations of the object proposals methods are provided. To overcome shortcomings of the original approach in case of handling small instances, we further propose our own network that clearly outperforms state-of-the-art methods for vehicle detection in aerial images. All experiments are performed on two publicly available datasets to account for differing characteristics such as ground sampling distance, number of objects per image and varying backgrounds.