Dynamic Scenario Segmentation based on Target Assumption Sort

DOI

10.2991/isrme-15.2015.283How to use a DOI?

Keywords

Dynamic scenario segmentation;Target assumption;Markov random field;Sorting

Abstract

This paper enables robust foreground segmentation by sorting target proposals over a assumption space to achieve consistent target candidates and binary segmentation of a video sequence. This is followed by sorting the target candidates over a specific hypothesis space to yield consistent and dense object proposals. An efficient higher-order graph-cut method is adopted to optimize a Markov Random Field (MRF) model, which is instantiated by the estimated foreground hypothesis with the highest score. Compared with a state-of-the-art algorithm, our method results in better and robust segmentation performance when dealing with highly dynamic image sequences.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zifen He
AU  - Yinhui Zhang
PY  - 2015/04
DA  - 2015/04
TI  - Dynamic Scenario Segmentation based on Target Assumption Sort
BT  - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
PB  - Atlantis Press
SP  - 1415
EP  - 1418
SN  - 1951-6851
UR  - https://doi.org/10.2991/isrme-15.2015.283
DO  - 10.2991/isrme-15.2015.283
ID  - He2015/04
ER  -