Title :
A Fast Motion Vector Estimation Method Based on Color Multidimension Projection
Author :
Wang Xiao-Ning ; Han Xiao-wei ; Yuan Zhong-hu ; Zhao Hong-ying
Author_Institution :
Sch. of Inf. Eng., Shenyang Univ., Shenyang, China
Abstract :
An approach of fast motion estimation (ME), aiming at the stabilization problem of video surveillance system on driving vehicle, is proposed in the paper. The information of color space based on multidimension projection and brightness based on grayscale projection (GP) are jointly considered. Compared with the traditional approaches of GP, the presented approach can be applied to achieve higher precision and remain real-time performance. Furthermore, it is more robust than GP, especially when brightness distribution of video image is nearly even. Meanwhile, scaling factor estimation is also applied, which is helpful to estimate motion vector(MV) from scaling motion mode.
Keywords :
image colour analysis; motion estimation; video surveillance; color multidimension projection; color space information; driving vehicle; fast motion estimation; fast motion vector estimation; grayscale projection; scaling motion mode; stabilization problem; video image; video surveillance system; Automotive engineering; Brightness; Genetic programming; Gray-scale; Image quality; Motion estimation; Multidimensional systems; Pattern matching; Vehicles; Video surveillance; DIS; motion vector estimation; multidimension projection (MP); scaling;
Conference_Titel :
Genetic and Evolutionary Computing, 2009. WGEC '09. 3rd International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-0-7695-3899-0
DOI :
10.1109/WGEC.2009.136