Simultaneous Camera Orientation Estimation and Road Target Tracking
2012 (English)In: Proceedings of the 15th International Conference on Information Fusion, IEEE , 2012, 802-807 p.Conference paper (Refereed)
Airborne surveillance systems equipped with a vision/infrared camera require good knowledge about the position and orientation of the camera for successful tracking of ground targets. In particular, this is essential when incorporating prior information, like road maps, that is expressed relative a global reference system. Usually, it is possible to obtain good positioning with inertial/satellite navigation systems, but estimating the orientation is generally more difficult. It might be possible to use SLAM (Simultaneous Localization and Mapping) or image registration approaches to support the navigation system, but not always since such approaches require stable features in the images. In this paper the problem of simultaneous orientation error estimation and road target tracking is considered by assuming that the target is constrained to a known road network. A particle filter approach is proposed and it is shown that the result of this filter is close to the performance of the ideal case where the orientation error is perfectly known. However, the performance depends on how informative the road path is and in rare cases the orientation error is unobservable.
Place, publisher, year, edition, pages
IEEE , 2012. 802-807 p.
Camera orientation, Estimation, Road target tracking
Signal Processing Control Engineering
IdentifiersURN: urn:nbn:se:liu:diva-85480ISBN: 978-0-9824438-4-2 (online)ISBN: 978-1-4673-0417-7 (print)ISBN: 978-0-9824438-5-9OAI: oai:DiVA.org:liu-85480DiVA: diva2:570672
International Conference on Information Fusion, Singapore, July 9-12, 2012
FunderSecurity LinkSwedish Research Council