A Study on Improving the Adaptive Background Method for Outdoor CCTV Object Tracking System

정도욱; HYUNG IL CHOI

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2015, 20(7), pp.17-24
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

정도욱 ¹ , HYUNG IL CHOI ²

¹ 숭실대학교
² 숭실대학교

ABSTRACT

In this paper, we propose a method to solve ghosting problem. To generate adaptive background, using an exponentially decreasing number of frames, may improve object detection performance. To extract moving objects from the background by using a differential image, detection error may be caused by object rotations or environmental changes. A ghosting problem can be issue-driven when there are outdoor environmental changes and moving objects. We studied that a differential image by adaptive background may reduce the ghosting problem. In experimental results, we test that our method can solve the ghosting problem.
KEYWORDS

Adaptive background subtraction , object tracking , Object detection , adaptive background
REFERENCES (11)

[journal] 장태우 / 2013 / A Study on the Object Extraction and Tracking System for Intelligent Surveillance / 한국통신학회논문지B / 한국통신학회 38 (7) : 589~595

[confproc] Xia, Dong / 2010 / Real-time infrared pedestrian detection based on multi-block LBP / ICCASM, 2010 International Conference on 12

[journal] Xu, Fengliang / 2008 / Pedestrian detection and tracking with night vision / Intelligent Transportation Systems / IEEE : 63~71

[journal] Zhang, Ruolin / 2012 / Object tracking and detecting based on adaptive background subtraction / Proceeding Engineering 29 : 1351~1355

[journal] 지영석 / 2010 / Robust Method of Updating Reference Background Image in Unstable Illumination Condition / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 15 (1) : 91~102

[journal] 배대희 / 2012 / Object Detection Using Predefined Gesture and Tracking / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 17 (10) : 43~53

[confproc] A. Elgammal / 2000 / Non-parametric model for background substraction / proc. 6th European Conference on Computer Vision

[confproc] Spagnolo, Paolo / 2006 / An abandoned/removed objects detection algorithm and its evaluation on pets datasets / Video and Signal Based Surveillance, 2006. AVSS'06. IEEE International Conference on

[confproc] Comaniciu, D / 2000 / Real-time tracking of non-rigid objects using mean shift / IEEE Conference on Computer Vision and Patern Recognition(CVPR) : 142~151

[report] Greg Welch / 1997 / An Introduction to the Kalman filter

[journal] Lucas, Bruce D. / 1981 / An iterative image registration technique with an application to stereo vision / IJCAI 81
KCI Citation (2)

KJC Korea
Journal Central

Statistics

Tools