Title :
Feature-based video stabilization for vehicular applications
Author :
Huang, Keng-Yen ; Tsai, Yi-Min ; Tsai, Chih-Chung ; Chen, Liang-Gee
Author_Institution :
DSP/IC Design Lab., Nat. Taiwan Univ., Taipei, Taiwan
Abstract :
This paper describes a method to stabilize video for vehicular applications based on Harris features and adaptive resolution. Lucas-Kanade method is applied to match feature points of consecutive frames and construct the feature motion flow. A damping filer is utilized to model the unwanted motion and global motion is separated by extracting oscillation. 92% correct rate with 0.54 second per frame is achieved. The provided benchmark shows outperformance of the proposed method.
Keywords :
feature extraction; image motion analysis; image resolution; video signal processing; Harris features; Lucas-Kanade method; adaptive resolution; damping filer; extracting oscillation; feature motion flow; feature-based video stabilization; match feature points; unwanted motion separation; vehicular applications; Application specific integrated circuits; Consumer electronics; Damping; Design engineering; Digital signal processing; Eigenvalues and eigenfunctions; Feature extraction; Frequency; Motion estimation; Vehicle safety;
Conference_Titel :
Consumer Electronics (ISCE), 2010 IEEE 14th International Symposium on
Conference_Location :
Braunschweig
Print_ISBN :
978-1-4244-6671-9
DOI :
10.1109/ISCE.2010.5522727
