Robust Segmentation of Highly Dynamic Scene with Missing Data

Yinhui ZHANG; Zifen HE; Changyu LIU

doi:10.1587/transinf.2014EDL8131

Robust Segmentation of Highly Dynamic Scene with Missing Data

Yinhui ZHANG, Zifen HE, Changyu LIU

Full Text Views

0

Cite this

Summary :

Segmenting foreground objects from highly dynamic scenes with missing data is very challenging. We present a novel unsupervised segmentation approach that can cope with extensive scene dynamic as well as a substantial amount of missing data that present in dynamic scene. To make this possible, we exploit convex optimization of total variation beforehand for images with missing data in which depletion mask is available. Inpainting depleted images using total variation facilitates detecting ambiguous objects from highly dynamic images, because it is more likely to yield areas of object instances with improved grayscale contrast. We use a conditional random field that adapts to integrate both appearance and motion knowledge of the foreground objects. Our approach segments foreground object instances while inpainting the highly dynamic scene with a variety amount of missing data in a coupled way. We demonstrate this on a very challenging dataset from the UCSD Highly Dynamic Scene Benchmarks (HDSB) and compare our method with two state-of-the-art unsupervised image sequence segmentation algorithms and provide quantitative and qualitative performance comparisons.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.1 pp.201-205

Publication Date: 2015/01/01

Publicized: 2014/09/29

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDL8131

Type of Manuscript: LETTER

Category: Pattern Recognition

Authors

Yinhui ZHANG
  Kunming University of Science and Technology
Zifen HE
  Kunming University of Science and Technology
Changyu LIU
  South China University of Technology

Keyword

image sequence segmentation, convex optimization, total variation, conditional random field

Cite this

Copy

Yinhui ZHANG, Zifen HE, Changyu LIU, "Robust Segmentation of Highly Dynamic Scene with Missing Data" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 1, pp. 201-205, January 2015, doi: 10.1587/transinf.2014EDL8131.
Abstract: Segmenting foreground objects from highly dynamic scenes with missing data is very challenging. We present a novel unsupervised segmentation approach that can cope with extensive scene dynamic as well as a substantial amount of missing data that present in dynamic scene. To make this possible, we exploit convex optimization of total variation beforehand for images with missing data in which depletion mask is available. Inpainting depleted images using total variation facilitates detecting ambiguous objects from highly dynamic images, because it is more likely to yield areas of object instances with improved grayscale contrast. We use a conditional random field that adapts to integrate both appearance and motion knowledge of the foreground objects. Our approach segments foreground object instances while inpainting the highly dynamic scene with a variety amount of missing data in a coupled way. We demonstrate this on a very challenging dataset from the UCSD Highly Dynamic Scene Benchmarks (HDSB) and compare our method with two state-of-the-art unsupervised image sequence segmentation algorithms and provide quantitative and qualitative performance comparisons.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8131/_p

Copy

@ARTICLE{e98-d_1_201,
author={Yinhui ZHANG, Zifen HE, Changyu LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Segmentation of Highly Dynamic Scene with Missing Data},
year={2015},
volume={E98-D},
number={1},
pages={201-205},
abstract={Segmenting foreground objects from highly dynamic scenes with missing data is very challenging. We present a novel unsupervised segmentation approach that can cope with extensive scene dynamic as well as a substantial amount of missing data that present in dynamic scene. To make this possible, we exploit convex optimization of total variation beforehand for images with missing data in which depletion mask is available. Inpainting depleted images using total variation facilitates detecting ambiguous objects from highly dynamic images, because it is more likely to yield areas of object instances with improved grayscale contrast. We use a conditional random field that adapts to integrate both appearance and motion knowledge of the foreground objects. Our approach segments foreground object instances while inpainting the highly dynamic scene with a variety amount of missing data in a coupled way. We demonstrate this on a very challenging dataset from the UCSD Highly Dynamic Scene Benchmarks (HDSB) and compare our method with two state-of-the-art unsupervised image sequence segmentation algorithms and provide quantitative and qualitative performance comparisons.},
keywords={},
doi={10.1587/transinf.2014EDL8131},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - Robust Segmentation of Highly Dynamic Scene with Missing Data
T2 - IEICE TRANSACTIONS on Information
SP - 201
EP - 205
AU - Yinhui ZHANG
AU - Zifen HE
AU - Changyu LIU
PY - 2015
DO - 10.1587/transinf.2014EDL8131
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2015
AB - Segmenting foreground objects from highly dynamic scenes with missing data is very challenging. We present a novel unsupervised segmentation approach that can cope with extensive scene dynamic as well as a substantial amount of missing data that present in dynamic scene. To make this possible, we exploit convex optimization of total variation beforehand for images with missing data in which depletion mask is available. Inpainting depleted images using total variation facilitates detecting ambiguous objects from highly dynamic images, because it is more likely to yield areas of object instances with improved grayscale contrast. We use a conditional random field that adapts to integrate both appearance and motion knowledge of the foreground objects. Our approach segments foreground object instances while inpainting the highly dynamic scene with a variety amount of missing data in a coupled way. We demonstrate this on a very challenging dataset from the UCSD Highly Dynamic Scene Benchmarks (HDSB) and compare our method with two state-of-the-art unsupervised image sequence segmentation algorithms and provide quantitative and qualitative performance comparisons.
ER -