Towards Real-time Motion Estimation in High-Definition Video Based on Points of Interest

0478548 - ÚI 2018 RIV PL eng C - Conference Paper (international conference)
Pulc, P. - Holeňa, Martin
Towards Real-time Motion Estimation in High-Definition Video Based on Points of Interest.
Proceedings of the 2017 Federated Conference on Computer Science and Information Systems. Warszawa: Polish Information Processing Society, 2017 - (Ganzha, M.; Maciaszek, L.; Paprzycki, M.), s. 67-70. Annals of Computer Science and Information Systems, 11. ISBN 978-83-946253-7-5. ISSN 2300-5963.
[FedCSIS 2017. Federated Conference on Computer Science and Information Systems. Prague (CZ), 03.09.2017-06.09.2017]
R&D Projects: GA ČR GA17-01251S
Institutional support: RVO:67985807
Keywords : motion estimation * visual descriptor * ORB * FLANN * video processing
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Currently used motion estimation is usually based on a computation of optical flow from individual images or short sequences. As these methods do not require an extraction of the visual description in points of interest, correspondence can be deduced only by the position of such points.
Permanent Link: http://hdl.handle.net/11104/0274643