Moving Target Detection Based on Double Model

Xin Ping Wu; Min Cang Fu

doi:10.4028/www.scientific.net/AMR.998-999.759

Paper Titles

Design on Control System of Automatic Sole Edge Grinding Machine Based on PLC
p.741

The Design of Signal Generator in Motor Function Rehabilitation Based on MCU
p.745

An Efficient Deadlock Avoidance Policy for FMS Using ROPN
p.751

Modeling and Simulation of Brushless DC Motor Speed Control System Based on MATLAB/SIMULINK
p.755

Moving Target Detection Based on Double Model
p.759

Study on Numerical Simulation of Shrapnel Fragments at the Components Damage Effect on Armored Vehicle Concept
p.763

Design of the Space-Based Optical Surveillance System Based on the Observation of Pinch Points Region on Earth Geostationary Orbit
p.768

A Theme-Oriented Data Automatic Organization Method
p.772

2D DOA Estimation Using Sparse Representation of Higher-Order Power of Covariance Matrix
p.779

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 998-999Moving Target Detection Based on Double Model

Moving Target Detection Based on Double Model

Abstract:

In order to overcome the problem that the single-Gauss model is poor of anti-interference and Gaussian Mixture model is poor of real-time, we present the double modeling algorithm of moving target detection. We use three frame difference method to distinguish the invariant region and complex region in background. And then we use single-Gauss modeling to model the invariant background while the complex region of background would be modeled with Gaussian Mixture modeling. It is more effective than the single-Gauss model and more efficient than the Gaussian Mixture model .The experimental results show that the improved algorithm is superior to the traditional single Gauss model or Gaussian Mixture model. It can detect moving target more quickly and accurately, with good robustness and real-time.

You might also be interested in these eBooks

Advances in Applied Sciences, Engineering and Technology II

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 998-999)

Pages:

759-762

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.998-999.759

Citation:

Cite this paper

Online since:

July 2014

Authors:

Xin Ping Wu*, Min Cang Fu

Keywords:

Double Modeling, Gaussian Mixture Modeling, Moving Object Detection, Single-Gauss Modeling

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Mao Yifang. Human motion recognition based on color image sequence in complex indoor environment [D]: [Master thesis. Chengdu: Xihua University, 2007: 1-3.

Google Scholar

[2] Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Fort Collins, Colorado, USA: IEEE Computer Society Press, 1999, pp.246-252.

DOI: 10.1109/cvpr.1999.784637

Google Scholar

[3] Wang Xiaoping, Zhang Lijie, Chang Ji. The improved method of moving target detection model based on single Gauss background [J]. computer engineering and application, 2009, 45 (21): 118-120.

Google Scholar

[4] Chen Huanzhong. Algorithm research of video motion detection target based on Gauss mixture model [D]: [Master thesis. Guangzhou: South China Normal University, 2008: 11-14.

Google Scholar

[5] Elgammal A, Harwood D, Davis LS. Non-parametric model for background subtraction[C]. In European Conference on Computer Vision, 2000: 751-767.

DOI: 10.1007/3-540-45053-x_48

Google Scholar