TY - GEN
T1 - On analyzing video with very small motions
AU - Dixon, Michael
AU - Abrams, Austin
AU - Jacobs, Nathan
AU - Pless, Robert
PY - 2011
Y1 - 2011
N2 - We characterize a class of videos consisting of very small but potentially complicated motions. We find that in these scenes, linear appearance variations have a direct relationship to scene motions. We show how to interpret appearance variations captured through a PCA decomposition of the image set as a scene-specific non-parametric motion basis. We propose fast, robust tools for dense flow estimates that are effective in scenes with small motions and potentially large image noise. We show example results in a variety of applications, including motion segmentation and long-term point tracking.
AB - We characterize a class of videos consisting of very small but potentially complicated motions. We find that in these scenes, linear appearance variations have a direct relationship to scene motions. We show how to interpret appearance variations captured through a PCA decomposition of the image set as a scene-specific non-parametric motion basis. We propose fast, robust tools for dense flow estimates that are effective in scenes with small motions and potentially large image noise. We show example results in a variety of applications, including motion segmentation and long-term point tracking.
UR - https://www.scopus.com/pages/publications/80052890824
UR - https://www.scopus.com/pages/publications/80052890824#tab=citedBy
U2 - 10.1109/CVPR.2011.5995703
DO - 10.1109/CVPR.2011.5995703
M3 - Conference contribution
AN - SCOPUS:80052890824
SN - 9781457703942
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1
EP - 8
BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
ER -