TY - GEN
T1 - Fast motion estimation using bi-directional gradient methods
AU - Keller, Y.
AU - Averbuch, Amir
N1 - Place of conference:USA
PY - 2002
Y1 - 2002
N2 - Gradient-based motion estimation methods (GMs) are considered to be in the heart of state-of-the-art registration algorithms, being able to account for both pixel and subpixel registration and to handle various motion models (translation, rotation, affine, and projective). These methods estimate the motion between two images based on the local changes in the image intensities while assuming image smoothness. This paper offers two main contributions. The first is enhancement of the GM technique by introducing two new bidirectional formulations of the GM. These improve the convergence properties for large motions. The second is that we present an analytical convergence analysis of the GM and its properties. Experimental results demonstrate the applicability of these algorithms to real images.
AB - Gradient-based motion estimation methods (GMs) are considered to be in the heart of state-of-the-art registration algorithms, being able to account for both pixel and subpixel registration and to handle various motion models (translation, rotation, affine, and projective). These methods estimate the motion between two images based on the local changes in the image intensities while assuming image smoothness. This paper offers two main contributions. The first is enhancement of the GM technique by introducing two new bidirectional formulations of the GM. These improve the convergence properties for large motions. The second is that we present an analytical convergence analysis of the GM and its properties. Experimental results demonstrate the applicability of these algorithms to real images.
UR - https://scholar.google.co.il/scholar?q=Fast+motion+estimation+using+bi-directional+gradient+methods&btnG=&hl=en&as_sdt=0%2C5
M3 - Conference contribution
BT - IEEE Transactions on Image Processing
PB - IEEE
ER -