Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera

Hsien Chou Liao, Po Yueh Chen, Zi Jun Lin, Zi Yi Lim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

High definition (HD) camera is widely used in surveillance systems. An HD camera with optical zoom is useful for monitoring a large area. However, it is inconvenient for a user to manually control the optical zoom for a long time. To exploit the functionality and extend the application domains of a HD camera, the zooming should be controlled automatically. Therefore, an automatic zooming mechanism is proposed in this paper. When the number of an object is small in the field of view (FOV) of the camera and an object is moving through the FOV, the zoom is controlled for capturing the object as clear as possible. A clear object image is useful for related image-based services, such as face recognition. In order to achieve the above goal, a Gaussian Mixture Model (GMM), temporal image differencing, a CamShift tracking method, and a Kalman filter are utilized for object detection and tracking. Then, an adaptive neuro-fuzzy inference system (ANFIS) is used to learn and determine a suitable value for adjusting the zoom. According to the experimental study of the prototype, the results show that the proposed mechanism is useful to capture the clear images of moving objects in a practical environment. A face detection algorithm is also used to demonstrate the feasibility of the captured clear images.

Original languageEnglish
Title of host publication19th International Conference on Advanced Communications Technology
Subtitle of host publicationOpening Era of Smart Society, ICACT 2017 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages869-876
Number of pages8
ISBN (Electronic)9788996865094
DOIs
Publication statusPublished - 2017 Mar 29
Event19th International Conference on Advanced Communications Technology, ICACT 2017 - Pyeongchang, Korea, Republic of
Duration: 2017 Feb 192017 Feb 22

Other

Other19th International Conference on Advanced Communications Technology, ICACT 2017
CountryKorea, Republic of
CityPyeongchang
Period17-02-1917-02-22

Fingerprint

Cameras
Face recognition
Fuzzy inference
Kalman filters
Monitoring

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Liao, H. C., Chen, P. Y., Lin, Z. J., & Lim, Z. Y. (2017). Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera. In 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding (pp. 869-876). [7890238] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ICACT.2017.7890238
Liao, Hsien Chou ; Chen, Po Yueh ; Lin, Zi Jun ; Lim, Zi Yi. / Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera. 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 869-876
@inproceedings{e6a9af8939e04e73b01da677ac5dd835,
title = "Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera",
abstract = "High definition (HD) camera is widely used in surveillance systems. An HD camera with optical zoom is useful for monitoring a large area. However, it is inconvenient for a user to manually control the optical zoom for a long time. To exploit the functionality and extend the application domains of a HD camera, the zooming should be controlled automatically. Therefore, an automatic zooming mechanism is proposed in this paper. When the number of an object is small in the field of view (FOV) of the camera and an object is moving through the FOV, the zoom is controlled for capturing the object as clear as possible. A clear object image is useful for related image-based services, such as face recognition. In order to achieve the above goal, a Gaussian Mixture Model (GMM), temporal image differencing, a CamShift tracking method, and a Kalman filter are utilized for object detection and tracking. Then, an adaptive neuro-fuzzy inference system (ANFIS) is used to learn and determine a suitable value for adjusting the zoom. According to the experimental study of the prototype, the results show that the proposed mechanism is useful to capture the clear images of moving objects in a practical environment. A face detection algorithm is also used to demonstrate the feasibility of the captured clear images.",
author = "Liao, {Hsien Chou} and Chen, {Po Yueh} and Lin, {Zi Jun} and Lim, {Zi Yi}",
year = "2017",
month = "3",
day = "29",
doi = "10.23919/ICACT.2017.7890238",
language = "English",
pages = "869--876",
booktitle = "19th International Conference on Advanced Communications Technology",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Liao, HC, Chen, PY, Lin, ZJ & Lim, ZY 2017, Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera. in 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding., 7890238, Institute of Electrical and Electronics Engineers Inc., pp. 869-876, 19th International Conference on Advanced Communications Technology, ICACT 2017, Pyeongchang, Korea, Republic of, 17-02-19. https://doi.org/10.23919/ICACT.2017.7890238

Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera. / Liao, Hsien Chou; Chen, Po Yueh; Lin, Zi Jun; Lim, Zi Yi.

19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. p. 869-876 7890238.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera

AU - Liao, Hsien Chou

AU - Chen, Po Yueh

AU - Lin, Zi Jun

AU - Lim, Zi Yi

PY - 2017/3/29

Y1 - 2017/3/29

N2 - High definition (HD) camera is widely used in surveillance systems. An HD camera with optical zoom is useful for monitoring a large area. However, it is inconvenient for a user to manually control the optical zoom for a long time. To exploit the functionality and extend the application domains of a HD camera, the zooming should be controlled automatically. Therefore, an automatic zooming mechanism is proposed in this paper. When the number of an object is small in the field of view (FOV) of the camera and an object is moving through the FOV, the zoom is controlled for capturing the object as clear as possible. A clear object image is useful for related image-based services, such as face recognition. In order to achieve the above goal, a Gaussian Mixture Model (GMM), temporal image differencing, a CamShift tracking method, and a Kalman filter are utilized for object detection and tracking. Then, an adaptive neuro-fuzzy inference system (ANFIS) is used to learn and determine a suitable value for adjusting the zoom. According to the experimental study of the prototype, the results show that the proposed mechanism is useful to capture the clear images of moving objects in a practical environment. A face detection algorithm is also used to demonstrate the feasibility of the captured clear images.

AB - High definition (HD) camera is widely used in surveillance systems. An HD camera with optical zoom is useful for monitoring a large area. However, it is inconvenient for a user to manually control the optical zoom for a long time. To exploit the functionality and extend the application domains of a HD camera, the zooming should be controlled automatically. Therefore, an automatic zooming mechanism is proposed in this paper. When the number of an object is small in the field of view (FOV) of the camera and an object is moving through the FOV, the zoom is controlled for capturing the object as clear as possible. A clear object image is useful for related image-based services, such as face recognition. In order to achieve the above goal, a Gaussian Mixture Model (GMM), temporal image differencing, a CamShift tracking method, and a Kalman filter are utilized for object detection and tracking. Then, an adaptive neuro-fuzzy inference system (ANFIS) is used to learn and determine a suitable value for adjusting the zoom. According to the experimental study of the prototype, the results show that the proposed mechanism is useful to capture the clear images of moving objects in a practical environment. A face detection algorithm is also used to demonstrate the feasibility of the captured clear images.

UR - http://www.scopus.com/inward/record.url?scp=85018512507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018512507&partnerID=8YFLogxK

U2 - 10.23919/ICACT.2017.7890238

DO - 10.23919/ICACT.2017.7890238

M3 - Conference contribution

AN - SCOPUS:85018512507

SP - 869

EP - 876

BT - 19th International Conference on Advanced Communications Technology

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Liao HC, Chen PY, Lin ZJ, Lim ZY. Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera. In 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding. Institute of Electrical and Electronics Engineers Inc. 2017. p. 869-876. 7890238 https://doi.org/10.23919/ICACT.2017.7890238