Real-time background subtraction based on GPGPU for high-resolution video surveillance

Sunhee Hwang; Kwangyong Lim; Youngjung Uh; Daeyong Park; Minsong Ki; Hyeran Byun

doi:10.1145/3022227.3022335

Real-time background subtraction based on GPGPU for high-resolution video surveillance

Sunhee Hwang, Kwangyong Lim, Youngjung Uh, Daeyong Park, Minsong Ki, Hyeran Byun

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

Demand for intelligent surveillance has been increasing, to automatically detect and prevent dangerous situations with surveillance cameras. Image analysis, the most essential element in intelligent surveillance system, has continuously developed and contributed to the improvement. To analyze surveillance videos, foreground segmentation is vital which require background modeling. This paper proposes background modeling method which is robust to illumination variation and shadow area. Also, the proposed method is applicable to high-resolution videos in real time with modification for GPU implementation. We validate our method on different types of dataset including our new benchmark dataset to analyze the result quantitatively and qualitatively. The execution time of proposed method is 228.2 FPS for High Definition videos with NVIDIA GTX660.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450348881
DOIs	https://doi.org/10.1145/3022227.3022335
Publication status	Published - 2017 Jan 5
Event	11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017 - Beppu, Japan Duration: 2017 Jan 5 → 2017 Jan 7

Publication series

Name	Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017

Other

Other	11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017
Country/Territory	Japan
City	Beppu
Period	17/1/5 → 17/1/7

Bibliographical note

Publisher Copyright:
© 2017 ACM.

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems

Access to Document

10.1145/3022227.3022335

Cite this

Hwang, S., Lim, K., Uh, Y., Park, D., Ki, M., & Byun, H. (2017). Real-time background subtraction based on GPGPU for high-resolution video surveillance. In Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017 [109] (Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017). Association for Computing Machinery, Inc. https://doi.org/10.1145/3022227.3022335

Hwang, Sunhee ; Lim, Kwangyong ; Uh, Youngjung et al. / Real-time background subtraction based on GPGPU for high-resolution video surveillance. Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc, 2017. (Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017).

@inproceedings{da40571e7e594371b5b9ee394db6509b,

title = "Real-time background subtraction based on GPGPU for high-resolution video surveillance",

abstract = "Demand for intelligent surveillance has been increasing, to automatically detect and prevent dangerous situations with surveillance cameras. Image analysis, the most essential element in intelligent surveillance system, has continuously developed and contributed to the improvement. To analyze surveillance videos, foreground segmentation is vital which require background modeling. This paper proposes background modeling method which is robust to illumination variation and shadow area. Also, the proposed method is applicable to high-resolution videos in real time with modification for GPU implementation. We validate our method on different types of dataset including our new benchmark dataset to analyze the result quantitatively and qualitatively. The execution time of proposed method is 228.2 FPS for High Definition videos with NVIDIA GTX660.",

author = "Sunhee Hwang and Kwangyong Lim and Youngjung Uh and Daeyong Park and Minsong Ki and Hyeran Byun",

note = "Publisher Copyright: {\textcopyright} 2017 ACM.; 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017 ; Conference date: 05-01-2017 Through 07-01-2017",

year = "2017",

month = jan,

day = "5",

doi = "10.1145/3022227.3022335",

language = "English",

series = "Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017",

}

Hwang, S, Lim, K, Uh, Y, Park, D, Ki, M & Byun, H 2017, Real-time background subtraction based on GPGPU for high-resolution video surveillance. in Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017., 109, Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017, Association for Computing Machinery, Inc, 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017, Beppu, Japan, 17/1/5. https://doi.org/10.1145/3022227.3022335

Real-time background subtraction based on GPGPU for high-resolution video surveillance. / Hwang, Sunhee; Lim, Kwangyong; Uh, Youngjung et al.

Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc, 2017. 109 (Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Real-time background subtraction based on GPGPU for high-resolution video surveillance

AU - Hwang, Sunhee

AU - Lim, Kwangyong

AU - Uh, Youngjung

AU - Park, Daeyong

AU - Ki, Minsong

AU - Byun, Hyeran

PY - 2017/1/5

Y1 - 2017/1/5

N2 - Demand for intelligent surveillance has been increasing, to automatically detect and prevent dangerous situations with surveillance cameras. Image analysis, the most essential element in intelligent surveillance system, has continuously developed and contributed to the improvement. To analyze surveillance videos, foreground segmentation is vital which require background modeling. This paper proposes background modeling method which is robust to illumination variation and shadow area. Also, the proposed method is applicable to high-resolution videos in real time with modification for GPU implementation. We validate our method on different types of dataset including our new benchmark dataset to analyze the result quantitatively and qualitatively. The execution time of proposed method is 228.2 FPS for High Definition videos with NVIDIA GTX660.

AB - Demand for intelligent surveillance has been increasing, to automatically detect and prevent dangerous situations with surveillance cameras. Image analysis, the most essential element in intelligent surveillance system, has continuously developed and contributed to the improvement. To analyze surveillance videos, foreground segmentation is vital which require background modeling. This paper proposes background modeling method which is robust to illumination variation and shadow area. Also, the proposed method is applicable to high-resolution videos in real time with modification for GPU implementation. We validate our method on different types of dataset including our new benchmark dataset to analyze the result quantitatively and qualitatively. The execution time of proposed method is 228.2 FPS for High Definition videos with NVIDIA GTX660.

UR - http://www.scopus.com/inward/record.url?scp=85015206877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015206877&partnerID=8YFLogxK

U2 - 10.1145/3022227.3022335

DO - 10.1145/3022227.3022335

M3 - Conference contribution

AN - SCOPUS:85015206877

T3 - Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017

BT - Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017

PB - Association for Computing Machinery, Inc

T2 - 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017

Y2 - 5 January 2017 through 7 January 2017

ER -

Hwang S, Lim K, Uh Y, Park D, Ki M, Byun H. Real-time background subtraction based on GPGPU for high-resolution video surveillance. In Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017. Association for Computing Machinery, Inc. 2017. 109. (Proceedings of the 11th International Conference on Ubiquitous Information Management and Communication, IMCOM 2017). doi: 10.1145/3022227.3022335

Real-time background subtraction based on GPGPU for high-resolution video surveillance

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this