DocumentCode :
548951
Title :
A new decoder side video stabilization using particle filter
Author :
Mohammadi, Masoud ; Fathi, Mahmood ; Soryani, Mohsen
Author_Institution :
Comput. Eng. Dept., Iran Univ. of Sci. & Technol., Teheran, Iran
fYear :
2011
fDate :
16-18 June 2011
Firstpage :
1
Lastpage :
4
Abstract :
Machine vision systems which are being extensively used for intelligent transportation applications, such as traffic monitoring and automatic navigation, suffer from image instability caused by environmental unstable conditions. On the other hand, increase in use of home video cameras and need to remove unwanted camera movements which caused by cameraman shaking hands, video stabilization algorithms are being considered. Motion estimation process is the main time consumer phase in video stabilization algorithms. In this paper, by extracting motion vectors from H.264 compressed video, motion estimation process is removed. Moreover, eliminating iterative outlier removal preprocessing and adaptive selection of motion vectors will increase the speed of algorithm. The proposed method was simulated and it was be demonstrated that the extracted motion parameters from motion vectors using particle filter can produce appropriate results for video stabilization problem.
Keywords :
computer vision; data compression; motion estimation; particle filtering (numerical methods); video coding; H.264 compressed video; automatic navigation; decoder side video stabilization; intelligent transportation applications; machine vision systems; motion estimation process; motion vectors; particle filter; traffic monitoring; Cameras; Equations; Estimation; Mathematical model; Motion estimation; Particle filters; Video sequences; H.264; Particle filter; Video stabilization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Signals and Image Processing (IWSSIP), 2011 18th International Conference on
Conference_Location :
Sarajevo
ISSN :
2157-8672
Print_ISBN :
978-1-4577-0074-3
Type :
conf
Filename :
5977354
Link To Document :
بازگشت