Title :
Real-Time Video Stabilization Based on Motion Compensation
Author :
Chen, Chao-Ho ; Kuo, Yi-Li ; Chen, Tsong-Yi ; Chen, Jie-Ru
Author_Institution :
Dept. of Electron. Eng., Nat. Kaohsiung Univ. of Appl. Sci., Kaohsiung, Taiwan
Abstract :
This paper presents a real-time video stabilization method based on motion compensation for adjusting unstable frames captured by a vibrating camera. The basic strategy is first to check if the frame is vibrant and then to analyze the vibration type and calculate the vibration degree for compensating the vibration area. Based on block motion estimation, a feature block selected from nine fixed observation blocks is used to obtain the vibration vector. With the vibration vector, the missing area can be compensated and the overlapping area is adjusted. Experimental results show that the proposed algorithm can effectively stabilize the video frames with moderate vibration in real-time.
Keywords :
cameras; feature extraction; motion compensation; real-time systems; video signal processing; camera vibration; feature block selection; motion compensation; real-time video stabilization; vibration vector; Cameras; Chaos; Motion compensation; Motion control; Motion estimation; Object recognition; Object segmentation; Video compression; Videoconference; Visual perception;
Conference_Titel :
Innovative Computing, Information and Control (ICICIC), 2009 Fourth International Conference on
Conference_Location :
Kaohsiung
Print_ISBN :
978-1-4244-5543-0
DOI :
10.1109/ICICIC.2009.305