An Object Detection Algorithm Based on Statistical Classification of Video Stream Pixels

Jun Song

doi:10.4028/www.scientific.net/AMR.962-965.2848

Paper Titles

Oil Analysis Cost-Effective Compressor Condition Computer Monitoring Technique
p.2827

Research on Improvement of Non-DEA Efficient Units
p.2831

A Novel Approach Automatic Detection of Suspicious Behavior
p.2838

An Improved ID3 Decision Tree Algorithm
p.2842

An Object Detection Algorithm Based on Statistical Classification of Video Stream Pixels
p.2848

Application Research of the Pro/3 Inference Information Report and Transformer Fault Diagnosis Based on Forward Reasoning
p.2852

Denoising Method for Calibration Data of Landing Guidance Radar Based on EMD and Wavelet
p.2856

Simulations of Three Navigation Mode of Wing-Diesel Ship
p.2863

Effective Data Structure for the Multidimensional Orthogonal Bin Packing Problems
p.2868

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 962-965An Object Detection Algorithm Based on Statistical...

An Object Detection Algorithm Based on Statistical Classification of Video Stream Pixels

Abstract:

Moving object detection and tracking based on the video stream are both challenging and very broad application prospects of research topics. This paper presents a object detection algorithm based on statistical classification of video stream pixels that can solve moving object detection in the background illumination mutations. The algorithm determines the number of points of light mutations by the statistical number of foreground pixels of the current frame. In the light mutations object detection uses relatively simple frame-difference method, otherwise it adopts the improved Gaussian mixture model method to model. Experimental results show that the algorithm can complete detecting in the light mutation quickly and accurately and has strong robustness.

You might also be interested in these eBooks

Resources and Sustainable Development III

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 962-965)

Pages:

2848-2851

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.962-965.2848

Citation:

Cite this paper

Online since:

June 2014

Authors:

Jun Song*

Keywords:

Background Modeling, Frame-Difference, Gaussian Mixture Models, Object Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Coifman B, Beymer D, Mclauchlan P, Malik J: A real-time computer vision system for vehicle tracking and traffic surveillance, Transportation Research Part C, Vol. 6, issue 4, pp.271-288. (1998).

DOI: 10.1016/s0968-090x(98)00019-9

Google Scholar

[2] Magee D: Tracking multiple vehicles using foreground, background and motion models, Image and Vision Computing, Vol. 22, issue 2, pp.143-155. (2004).

DOI: 10.1016/s0262-8856(03)00145-8

Google Scholar

[3] McKenna S et al: Tracking groups of people, Computer Vision and Image Understanding, Vol. 80, issue 1, pp.42-56. (2000).

Google Scholar

[4] Koller D, Daniilidis K, Nagel H: Model-based object tracking in monocular image sequences of road traffic scene, International Journal of Computer Vision, Vol. 10, issue 3, pp.257-281. (1993).

DOI: 10.1007/bf01539538

Google Scholar

[5] Stauffer C, Grimson W: Learning patterns of activity using real-time tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, issue 8, pp.747-757. (2000).

DOI: 10.1109/34.868677

Google Scholar