Sunshine-Change-Tolerant Moving Object Masking for Realizing both Privacy Protection and Video Surveillance
Summary :
Recently, video surveillance systems have been widely introduced in various places, and protecting the privacy of objects in the scene has been as important as ensuring security. Masking each moving object with a background subtraction method is an effective technique to protect its privacy. However, the background subtraction method is heavily affected by sunshine change, and a redundant masking by over-extraction is inevitable. Such superfluous masking disturbs the quality of video surveillance. In this paper, we propose a moving object masking method combining background subtraction and machine learning based on Real AdaBoost. This method can reduce the superfluous masking while maintaining the reliability of privacy protection. In the experiments, we demonstrate that the proposed method achieves about 78-94% accuracy for classifying superfluous masking regions and moving objects.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.9 pp.2483-2492
- Publication Date
- 2014/09/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2013EDP7465
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Yoichi TOMIOKA
Tokyo University of Agriculture and Technology
Hikaru MURAKAMI
Tokyo University of Agriculture and Technology
Hitoshi KITAZAWA
Tokyo University of Agriculture and Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yoichi TOMIOKA, Hikaru MURAKAMI, Hitoshi KITAZAWA, "Sunshine-Change-Tolerant Moving Object Masking for Realizing both Privacy Protection and Video Surveillance" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 9, pp. 2483-2492, September 2014, doi: 10.1587/transinf.2013EDP7465.
Abstract: Recently, video surveillance systems have been widely introduced in various places, and protecting the privacy of objects in the scene has been as important as ensuring security. Masking each moving object with a background subtraction method is an effective technique to protect its privacy. However, the background subtraction method is heavily affected by sunshine change, and a redundant masking by over-extraction is inevitable. Such superfluous masking disturbs the quality of video surveillance. In this paper, we propose a moving object masking method combining background subtraction and machine learning based on Real AdaBoost. This method can reduce the superfluous masking while maintaining the reliability of privacy protection. In the experiments, we demonstrate that the proposed method achieves about 78-94% accuracy for classifying superfluous masking regions and moving objects.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2013EDP7465/_p
Copy
@ARTICLE{e97-d_9_2483,
author={Yoichi TOMIOKA, Hikaru MURAKAMI, Hitoshi KITAZAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Sunshine-Change-Tolerant Moving Object Masking for Realizing both Privacy Protection and Video Surveillance},
year={2014},
volume={E97-D},
number={9},
pages={2483-2492},
abstract={Recently, video surveillance systems have been widely introduced in various places, and protecting the privacy of objects in the scene has been as important as ensuring security. Masking each moving object with a background subtraction method is an effective technique to protect its privacy. However, the background subtraction method is heavily affected by sunshine change, and a redundant masking by over-extraction is inevitable. Such superfluous masking disturbs the quality of video surveillance. In this paper, we propose a moving object masking method combining background subtraction and machine learning based on Real AdaBoost. This method can reduce the superfluous masking while maintaining the reliability of privacy protection. In the experiments, we demonstrate that the proposed method achieves about 78-94% accuracy for classifying superfluous masking regions and moving objects.},
keywords={},
doi={10.1587/transinf.2013EDP7465},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Sunshine-Change-Tolerant Moving Object Masking for Realizing both Privacy Protection and Video Surveillance
T2 - IEICE TRANSACTIONS on Information
SP - 2483
EP - 2492
AU - Yoichi TOMIOKA
AU - Hikaru MURAKAMI
AU - Hitoshi KITAZAWA
PY - 2014
DO - 10.1587/transinf.2013EDP7465
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2014
AB - Recently, video surveillance systems have been widely introduced in various places, and protecting the privacy of objects in the scene has been as important as ensuring security. Masking each moving object with a background subtraction method is an effective technique to protect its privacy. However, the background subtraction method is heavily affected by sunshine change, and a redundant masking by over-extraction is inevitable. Such superfluous masking disturbs the quality of video surveillance. In this paper, we propose a moving object masking method combining background subtraction and machine learning based on Real AdaBoost. This method can reduce the superfluous masking while maintaining the reliability of privacy protection. In the experiments, we demonstrate that the proposed method achieves about 78-94% accuracy for classifying superfluous masking regions and moving objects.
ER -
English
