Sciweavers

CVPR
2008
IEEE

Local grouping for optical flow

15 years 23 days ago
Local grouping for optical flow
Optical flow estimation requires spatial integration, which essentially poses a grouping question: what points belong to the same motion and what do not. Classical local approaches to optical flow, such as Lucas-Kanade, use isotropic neighborhoods and have considerable difficulty near motion boundaries. In this work we utilize imagebased grouping to facilitate spatial- and scale-adaptive integration. We define soft spatial support using pairwise affinities computed through intervening contour. We sample images at edges and corners, and iteratively estimate affine motion at sample points. Figure-ground organization further improves grouping and flow estimation near boundaries. We show that affinity-based spatial integration enables reliable flow estimation and avoids erroneous motion propagation from and/or across object boundaries. We demonstrate our approach on the Middlebury flow dataset.
Xiaofeng Ren
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Xiaofeng Ren
Comments (0)