Object Segmentation Using Structural Relationship between Super-pixels

DOI

10.2991/nceece-15.2016.125How to use a DOI?

Keywords

Segmentation; Super-pixels; Structural Relationship; CRF; Patches

Abstract

We address the problem of describing and integrating long range information efficiently, such as the information demonstrated by super-pixels (patches), into conditional random field (CRF) model for object segmentation. For those purpose, a novel structural relationship between patches are defined for evaluating super-pixels’ similarity. The structural relationship between super-pixels will focus on whether two patches can display similar information of objects’ global appearance. Furthermore, a regression model is learned for super-pixels classification based on analyzing their structural relationship between super pixels and initial object hypothesis. Finally, a pixel-level CRF model that integrates information of color, texture and super-pixels is constructed to obtain segmentation results. Compared with traditional super-pixels or solely pixels based model, our method can combine the complementary information provided by pixels and super-pixels and generate better performance.

Copyright

© 2016, 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  - Yonghui Gao
AU  - Lei Zhou
AU  - Xiaoxiao Li
PY  - 2015/12
DA  - 2015/12
TI  - Object Segmentation Using Structural Relationship between Super-pixels
BT  - Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 674
EP  - 681
SN  - 2352-5401
UR  - https://doi.org/10.2991/nceece-15.2016.125
DO  - 10.2991/nceece-15.2016.125
ID  - Gao2015/12
ER  -