DocumentCode :
3402305
Title :
FH-adaptive motion compensation for moving object detection in an active camera
Author :
Kim, Jiman ; Shin, Jongju ; Kim, Daijin
Author_Institution :
Dept. of Comput. Sci. & Eng., Pohang Univ. of Sci. & Technol., Pohang, South Korea
fYear :
2009
fDate :
14-17 Dec. 2009
Firstpage :
532
Lastpage :
537
Abstract :
An efficient camera motion compensation algorithm based on multi-layer decomposition is proposed for moving object detection in an active camera. Optical flow map obtained using the pyramid LK algorithm is divided into multi-layers by flow histogram decomposition. The camera motion model parameters of each layer are computed and used to compensate for the motion. The proposed algorithm has more accurate motion compensation and moving object detection results than the existing single-layer motion models. Also, the proposed algorithm is fast, so it can be applied to real time systems.
Keywords :
cameras; motion compensation; motion estimation; object detection; FH-adaptive motion compensation; active camera; flow histogram decomposition; moving object detection; multilayer decomposition; optical flow map; pyramid Lucas-Kanabe algorithm; real time system; Histograms; Image motion analysis; Iterative algorithms; Maximum likelihood estimation; Motion compensation; Motion estimation; Object detection; Optical computing; Real time systems; Smart cameras;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Information Technology (ISSPIT), 2009 IEEE International Symposium on
Conference_Location :
Ajman
Print_ISBN :
978-1-4244-5949-0
Type :
conf
DOI :
10.1109/ISSPIT.2009.5407543
Filename :
5407543
Link To Document :
بازگشت