DocumentCode :
3549158
Title :
Integration of motion fields through shape
Author :
Ji, Hui ; Fermüller, Cornelia
Author_Institution :
Center for Autom. Res., Maryland Univ., College Park, MD, USA
Volume :
2
fYear :
2005
fDate :
20-25 June 2005
Firstpage :
663
Abstract :
Structure from motion from single flow fields has been studied intensively, but the integration of information from multiple flow fields has not received much attention. Here we address this problem by enforcing constraints on the shape (surface normals) of the scene in view, as opposed to constraints on the structure (depth). The advantage of integrating shape is two-fold. First, we do not need to estimate feature correspondences over multiple frames, but we only need to match patches. Second, the shape vectors in the different views are related only by rotation. This constraint on shape can be combined easily with motion estimation, thus formulating motion and structure estimation from multiple views as a practical constrained minimization problem using a rank-3 constraint. Based on this constraint, we develop a 3D motion technique, which locates through color and motion segmentation, planar patches in the scene, matches patches over multiple frames, and estimates the motion between multiple frames and the shape of the selected scene patches using the image gradients. Experiments evaluate the accuracy of the 3D motion estimation and demonstrate the motion and shape estimation of the technique by super-resolving an image sequence.
Keywords :
computational geometry; image colour analysis; image resolution; image segmentation; image sequences; minimisation; motion estimation; 3D motion estimation; constrained minimization problem; image gradients; image sequence; motion field integration; motion segmentation; planar patches; rank-3 constraint; scene patches; shape estimation; structure estimation; Automation; Cameras; Computer vision; Educational institutions; Image resolution; Layout; Motion estimation; Motion segmentation; Parameter estimation; Shape; 3D motion estimation; decoupling translation from rotation; integration of motion fields; shape and rotation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2372-2
Type :
conf
DOI :
10.1109/CVPR.2005.190
Filename :
1467505
Link To Document :
بازگشت