Title :
Reconstruction of frame backgrounds using camera parameters and a background panorama
Author :
Xuedong, Liu ; Ning, Zhao
Author_Institution :
Sch. of Inf. Eng., Wuhan Univ. of Technol., Wuhan, China
Abstract :
In a video surveillance system, the background extraction of video frames plays an important role for the segmentation and recognition of surveillance objects, and even video compression. Since a video frame background can be obtained by tailoring a background panorama, a theoretical relation between the frame background and camera parameters along with a high resolution background panorama is established through the imaging geometry in this paper. An application instance shows that the deduced formula can reconstruct correctly video frame backgrounds, and on this basis, surveillance objects can be segmented easily.
Keywords :
cameras; feature extraction; image reconstruction; image segmentation; object recognition; video surveillance; background panorama; camera parameters; frame backgrounds reconstruction; surveillance objects recognition; surveillance objects segmentation; video compression; video frames background extraction; video surveillance system; Cameras; Image reconstruction; Motion estimation; Streaming media; Video surveillance; background reconstruction; camera parameters; panorama; video surveillance;
Conference_Titel :
Electronics, Communications and Control (ICECC), 2011 International Conference on
Conference_Location :
Ningbo
Print_ISBN :
978-1-4577-0320-1
DOI :
10.1109/ICECC.2011.6066642