Learning layered motion segmentations of video
Mudigonda Pawan Kumar, Philip Torr and Andrew Zisserman
In: ICCV 2005, 17-20 Oct 2005, Beijing, China.
We present an unsupervised approach for learning a generative layered
representation of a scene from a video for motion segmentation. The learnt
model is a composition of layers, which consist of one or more
segments. Included in the model are the effects of image projection,
lighting, and motion blur.
The two main contributions of our method are: (i) A novel algorithm for
obtaining the initial estimate of the model using efficient loopy belief
propagation; (ii) Using $\alpha\beta$-swap and $\alpha$-expansion
algorithms, which guarantee a strong local minima, for refining the initial
estimate. Results are presented on several classes of objects with different
types of camera motion. We compare our method with the state of the art and
demonstrate significant improvements.
|EPrint Type:||Conference or Workshop Item (Oral)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Mudigonda Pawan Kumar|
|Deposited On:||08 September 2005|