Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera

Yuxiang Sun; Ming Liu; Max Q.-H. Meng

doi:10.1109/ROBIO.2017.8324393

Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera

Yuxiang Sun
, Ming Liu
, Max Q.-H. Meng

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

12 Citations (Scopus)

Abstract

Scene modelling is of great importance for robots in unknown environments. Existing Visual Simultaneous Localization and Mapping (Visual SLAM) approaches are able to build impressive scene models using RGB-D cameras in static scenes. In dynamic scenes, however, moving objects can be recorded as spurious objects, which contaminates the resulting scene models. In order to build clear scene models, we propose a novel moving-object removal approach for scene modelling algorithms in this paper. Our approach does not rely on prior knowledge, such as appearance features or initial segmentation. In addition, the proposed approach does not require an initialization process, which is different from most background subtraction algorithms. The experimental results demonstrate that our approach is able to effectively remove moving objects and assist scene modelling algorithms to build clear models in dynamic scenes. © 2017 IEEE.

Original language	English
Title of host publication	2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017
Publisher	IEEE
Pages	50-55
Volume	2018-January
ISBN (Print)	9781538637418
DOIs	https://doi.org/10.1109/ROBIO.2017.8324393
Publication status	Published - 2 Jul 2017
Externally published	Yes
Event	2017 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2017) - The Parisian Macao, Macao, China Duration: 5 Dec 2017 → 8 Dec 2017 http://2017.ieee-robio.org/

Publication series

Name	2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017
Volume	2018-January

Conference

Conference	2017 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2017)
Place	Macao, China
Period	5/12/17 → 8/12/17
Internet address	http://2017.ieee-robio.org/

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Funding

Research presented in this paper was supported by the Shenzhen Science and Technology Program Project No. JCYJ20170413161616163 awarded to Prof. Max Q.-H. Meng.

Access Output

10.1109/ROBIO.2017.8324393

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Sun, Y., Liu, M., & Meng, M. Q.-H. (2017). Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera. In 2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017 (Vol. 2018-January, pp. 50-55). (2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017; Vol. 2018-January). IEEE. https://doi.org/10.1109/ROBIO.2017.8324393

@inproceedings{e7ad86627a134946a256b258be8f8545,

title = "Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera",

abstract = "Scene modelling is of great importance for robots in unknown environments. Existing Visual Simultaneous Localization and Mapping (Visual SLAM) approaches are able to build impressive scene models using RGB-D cameras in static scenes. In dynamic scenes, however, moving objects can be recorded as spurious objects, which contaminates the resulting scene models. In order to build clear scene models, we propose a novel moving-object removal approach for scene modelling algorithms in this paper. Our approach does not rely on prior knowledge, such as appearance features or initial segmentation. In addition, the proposed approach does not require an initialization process, which is different from most background subtraction algorithms. The experimental results demonstrate that our approach is able to effectively remove moving objects and assist scene modelling algorithms to build clear models in dynamic scenes. {\textcopyright} 2017 IEEE.",

author = "Yuxiang Sun and Ming Liu and Meng, \{Max Q.-H.\}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected]. ; 2017 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2017) ; Conference date: 05-12-2017 Through 08-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ROBIO.2017.8324393",

language = "English",

isbn = "9781538637418",

volume = "2018-January",

series = "2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017",

publisher = "IEEE",

pages = "50--55",

booktitle = "2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017",

address = "United States",

url = "http://2017.ieee-robio.org/",

}

Sun, Y, Liu, M & Meng, MQ-H 2017, Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera. in 2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017. vol. 2018-January, 2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017, vol. 2018-January, IEEE, pp. 50-55, 2017 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2017), Macao, China, 5/12/17. https://doi.org/10.1109/ROBIO.2017.8324393

Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera. / Sun, Yuxiang; Liu, Ming; Meng, Max Q.-H.
2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017. Vol. 2018-January IEEE, 2017. p. 50-55 (2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017; Vol. 2018-January).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Invisibility

T2 - 2017 IEEE International Conference on Robotics and Biomimetics (IEEE-ROBIO 2017)

AU - Sun, Yuxiang

AU - Liu, Ming

AU - Meng, Max Q.-H.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Scene modelling is of great importance for robots in unknown environments. Existing Visual Simultaneous Localization and Mapping (Visual SLAM) approaches are able to build impressive scene models using RGB-D cameras in static scenes. In dynamic scenes, however, moving objects can be recorded as spurious objects, which contaminates the resulting scene models. In order to build clear scene models, we propose a novel moving-object removal approach for scene modelling algorithms in this paper. Our approach does not rely on prior knowledge, such as appearance features or initial segmentation. In addition, the proposed approach does not require an initialization process, which is different from most background subtraction algorithms. The experimental results demonstrate that our approach is able to effectively remove moving objects and assist scene modelling algorithms to build clear models in dynamic scenes. © 2017 IEEE.

AB - Scene modelling is of great importance for robots in unknown environments. Existing Visual Simultaneous Localization and Mapping (Visual SLAM) approaches are able to build impressive scene models using RGB-D cameras in static scenes. In dynamic scenes, however, moving objects can be recorded as spurious objects, which contaminates the resulting scene models. In order to build clear scene models, we propose a novel moving-object removal approach for scene modelling algorithms in this paper. Our approach does not rely on prior knowledge, such as appearance features or initial segmentation. In addition, the proposed approach does not require an initialization process, which is different from most background subtraction algorithms. The experimental results demonstrate that our approach is able to effectively remove moving objects and assist scene modelling algorithms to build clear models in dynamic scenes. © 2017 IEEE.

UR - https://www.scopus.com/pages/publications/85049925059

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85049925059&origin=recordpage

U2 - 10.1109/ROBIO.2017.8324393

DO - 10.1109/ROBIO.2017.8324393

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781538637418

VL - 2018-January

T3 - 2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017

SP - 50

EP - 55

BT - 2017 IEEE International Conference on Robotics and Biomimetics, ROBIO 2017

PB - IEEE

Y2 - 5 December 2017 through 8 December 2017

ER -

Invisibility: A moving-object removal approach for dynamic scene modelling using RGB-D camera

Abstract

Publication series

Conference

Bibliographical note

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this