Segmentation of moving objects by long term video analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(6): 1187 - 1200, Jun 2014
Abstract: Motion is a strong cue for unsupervised object-level grouping. In this paper, we demonstrate that motion will be exploited most effectively, if it is regarded over larger time windows. Opposed to classical two-frame optical flow, point trajectories that span hundreds of frames are less susceptible to short term variations that hinder separating different objects. As a positive side effect, the resulting groupings are temporally consistent over a whole video shot, a property that requires tedious post-processing in the vast majority of existing approaches. We suggest working with a paradigm that starts with semi-dense motion cues first and that fills up textureless areas afterwards based on color. This paper also contributes the Freiburg-Berkeley motion segmentation (FBMS) dataset, a large, heterogeneous benchmark with 59 sequences and pixel-accurate ground truth annotation of moving objects.
Publisher's link
DownloadsImages and movies
BibTex reference
@Article{OB14b, author = "P. Ochs and J. Malik and T. Brox", title = "Segmentation of moving objects by long term video analysis", journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence", number = "6", volume = "36", pages = "1187 - 1200", month = "Jun", year = "2014", note = "Preprint", url = "http://lmb.informatik.uni-freiburg.de/Publications/2014/OB14b" }