Modeling depth for nonparametric foreground segmentation using RGBD devices

Gabriel Moyà-Alcover; Ahmed Elgammal; Antoni Jaume-i-Capó; Javier Varona

doi:https://doi.org/10.1016/j.patrec.2016.09.004

Modeling depth for nonparametric foreground segmentation using RGBD devices

Gabriel Moyà-Alcover, Ahmed Elgammal, Antoni Jaume-i-Capó, Javier Varona

SAS - Computer Science

Rutgers, The State University

Research output: Contribution to journal › Article › peer-review

17 Scopus citations

Abstract

The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve foreground segmentation. In this work, we present a new nonparametric approach where a unified model mixes the device multiple information cues. In order to unify all the device channel cues, a new probabilistic depth data model is also proposed where we show how to handle the inaccurate data to improve foreground segmentation. A new RGBD video dataset is presented in order to introduce a new standard for comparison purposes of this kind of algorithms. Results show that the proposed approach can handle several practical situations and obtain good results in all cases.

Original language	English (US)
Pages (from-to)	76-85
Number of pages	10
Journal	Pattern Recognition Letters
Volume	96
DOIs	https://doi.org/10.1016/j.patrec.2016.09.004
State	Published - Sep 1 2017

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Keywords

Absent depth observations
Background subtraction
Moving object detection
Non-parametric estimation
RGBD dataset

Access to Document

https://doi.org/10.1016/j.patrec.2016.09.004

Cite this

@article{a020826f32bc48df8bdf2f23f2d94dd8,

title = "Modeling depth for nonparametric foreground segmentation using RGBD devices",

abstract = "The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve foreground segmentation. In this work, we present a new nonparametric approach where a unified model mixes the device multiple information cues. In order to unify all the device channel cues, a new probabilistic depth data model is also proposed where we show how to handle the inaccurate data to improve foreground segmentation. A new RGBD video dataset is presented in order to introduce a new standard for comparison purposes of this kind of algorithms. Results show that the proposed approach can handle several practical situations and obtain good results in all cases.",

keywords = "Absent depth observations, Background subtraction, Moving object detection, Non-parametric estimation, RGBD dataset",

author = "Gabriel Moy{\`a}-Alcover and Ahmed Elgammal and Antoni Jaume-i-Cap{\'o} and Javier Varona",

note = "Funding Information: This work was partially funded by the Project TIN2012-35427 of the Spanish Government, with FEDER support. Publisher Copyright: {\textcopyright} 2016 Elsevier B.V.",

year = "2017",

month = sep,

day = "1",

doi = "https://doi.org/10.1016/j.patrec.2016.09.004",

language = "English (US)",

volume = "96",

pages = "76--85",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

}

TY - JOUR

T1 - Modeling depth for nonparametric foreground segmentation using RGBD devices

AU - Moyà-Alcover, Gabriel

AU - Elgammal, Ahmed

AU - Jaume-i-Capó, Antoni

AU - Varona, Javier

PY - 2017/9/1

Y1 - 2017/9/1

N2 - The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve foreground segmentation. In this work, we present a new nonparametric approach where a unified model mixes the device multiple information cues. In order to unify all the device channel cues, a new probabilistic depth data model is also proposed where we show how to handle the inaccurate data to improve foreground segmentation. A new RGBD video dataset is presented in order to introduce a new standard for comparison purposes of this kind of algorithms. Results show that the proposed approach can handle several practical situations and obtain good results in all cases.

AB - The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve foreground segmentation. In this work, we present a new nonparametric approach where a unified model mixes the device multiple information cues. In order to unify all the device channel cues, a new probabilistic depth data model is also proposed where we show how to handle the inaccurate data to improve foreground segmentation. A new RGBD video dataset is presented in order to introduce a new standard for comparison purposes of this kind of algorithms. Results show that the proposed approach can handle several practical situations and obtain good results in all cases.

KW - Absent depth observations

KW - Background subtraction

KW - Moving object detection

KW - Non-parametric estimation

KW - RGBD dataset

UR - http://www.scopus.com/inward/record.url?scp=85001060828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85001060828&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.patrec.2016.09.004

DO - https://doi.org/10.1016/j.patrec.2016.09.004

M3 - Article

VL - 96

SP - 76

EP - 85

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -

Modeling depth for nonparametric foreground segmentation using RGBD devices

Abstract

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this