
Publica
Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten. Moving object detection and segmentation for remote aerial video surveillance
:
Volltext urn:nbn:de:0072-449223 (18 MByte PDF) MD5 Fingerprint: 588f3e54d4101679f2c464902c6d4521 Erstellt am: 24.3.2015 |
| Karlsruhe: KIT Scientific Publishing, 2015, XI, 215 S. Zugl.: Karlsruhe, Inst. für Technologie (KIT), Diss., 2014 Karlsruher Schriften zur Anthropomatik, 18 ISBN: 978-3-7315-0320-0 |
|
| Englisch |
| Dissertation, Elektronische Publikation |
| Fraunhofer IOSB () |
Abstract
Unmanned Aerial Vehicles (UAVs) equipped with video cameras are a flexible support to ensure civil and military safety and security. In this thesis, a video processing chain is presented for moving object detection in aerial video surveillance. A Track-Before-Detect (TBD) algorithm is applied to detect motion that is independent of the camera motion. Novel robust and fast object detection and segmentation approaches improve the baseline TBD and outperform current state-of-the-art methods.