Global motion estimation using variable block sizes and its application to object segmentation
Autor: | Andreas Krutz, Marta Mrak, Ahmet M. Kondoz, Alexander Glantz, Thomas Sikora, Marina Georgia Arvanitidou |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2009 |
Předmět: |
Motion compensation
business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Quarter-pixel motion Global Motion Estimation Variable Block Sizes Object Segmentation Motion field Motion estimation Computer vision Artificial intelligence business Block size Block-matching algorithm Block (data storage) Data compression |
Zdroj: | WIAMIS |
Popis: | Global motion is estimated either in the pixel domain or in block based domain. Until now, all the approaches regarding the latter are based on fixed sized blocks while the recent compression methods tend to use variable block sizes during motion estimation. In this paper we present a new procedure for global motion estimation based on a variable block size motion vector field. A block matching algorithm which is able to adapt the block size according to the motion complexity within the frame is used. The resulting motion vectors are employed for global motion estimation. Furthermore, binary foreground-background masks are created based on the frame-by-frame motion compensated differences by exploiting spatial conditions through anisotropic diffusion filtering. For global motion estimation the performance evaluation in terms of background PSNR shows an enhancement of more than 2.5 dB in the well-known “Stefan” sequence, compared to the conventional case of fixed block size, at a reasonable implementation complexity. |
Databáze: | OpenAIRE |
Externí odkaz: |