Mathematical Optimization for Data Science Group, Saarland University

Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

Home
Teaching
Research
Publications
Job Offers

Saarland
University

Mathematics
and

Computer Science

Segmentation of moving objects by long term video analysis

P. Ochs, J. Malik and T. Brox

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.



pdf	Bibtex	Publisher's link	Code

Citation:
P. Ochs, J. Malik, T. Brox:
Segmentation of moving objects by long term video analysis.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(6):1187-1200, 2014.

Bibtex:
@article{OB14b, title = {Segmentation of moving objects by long term video analysis}, author = {P. Ochs and J. Malik and T. Brox}, year = {2014}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {6}, volume = {36}, pages = {1187--1200} }

Impressum
Datenschutz