Hierarchy of Localized Random Forests for Video Annotation
Pattern Recognition (Proc. DAGM), Springer, LNCS , 2012
Abstract: We address the problem of annotating a video sequence with
partial supervision. Given the pixel-wise annotations in the first frame,
we aim to propagate these labels ideally throughout the whole video.
While some labels can be propagated using optical flow, disocclusion
and unreliable flow in some areas require additional cues. To this end,
we propose to train localized classifiers on the annotated frame. In con-
trast to a global classifier, localized classifiers allow to distinguish colors
that appear in both the foreground and the background but at very dif-
ferent locations. We design a multi-scale hierarchy of localized random
forests, which collectively takes a decision. Cues from optical flow and
the classifier are combined in a variational framework. The approach
can deal with multiple objects in a video. We present qualitative and
quantitative results on the Berkeley Motion Segmentation Dataset.
Images and movies
BibTex reference
@InProceedings{NOLB12, author = "N.S.Nagaraja and P.Ochs and K.Liu and T.Brox", title = "Hierarchy of Localized Random Forests for Video Annotation", booktitle = "Pattern Recognition (Proc. DAGM)", year = "2012", publisher = "Springer, LNCS ", url = "http://lmb.informatik.uni-freiburg.de/Publications/2012/NOLB12" }