Metadata language
Wielo-kadrowa analiza obrazów w zagadnieniach rozszerzonej rzeczywistości
Subtitle:Raport Badawczy = Research Report ; RB/61/2010
Creator: Publisher:Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences
Place of publishing: Date issued/created: Description:112-122 stron ; 21 cm ; Bibliografia s. 121-122
Abstract:The paper deals with the recognition ofthe same or similar objects in the different movie sequences. The recognition algorithm based on epipolar geometry constraints is presented. This algorithm consists from three main functional blocks. The first block selects characteristic points of the frame using the corner detection methods. The second block employs RANSAC method to eliminate outliners among the selected points that cannot be matched between frames. The last block determines the location of real image points using epipolar geometry as well as the minimization of a distance function. Levenberg - Marquad algorithm is used as optimization method. Moreover the application of the described algorithm in Augmented Reality problems is discussed.
Relation:Raport Badawczy = Research Report
Resource type: Detailed Resource Type: Source: Language: Language of abstract: Rights:Licencja Creative Commons Uznanie autorstwa 4.0
Terms of use:Zasób chroniony prawem autorskim. [CC BY 4.0 Międzynarodowe] Korzystanie dozwolone zgodnie z licencją Creative Commons Uznanie autorstwa 4.0, której pełne postanowienia dostępne są pod adresem: ; -
Digitizing institution:Instytut Badań Systemowych Polskiej Akademii Nauk
Original in:Biblioteka Instytutu Badań Systemowych PAN
Projects co-financed by: Access: