Modified Object Tracking and Counting Method Based on Gaussian Mixture Model

Ming Jie Zhang; Bao Sheng Kang

doi:10.4028/www.scientific.net/AMM.373-375.598

Paper Titles

A Multi-Rate Implementation of Auditory Filter Bank
p.579

Research on Improved Methods of Watershed Algorithm
p.583

Comparison about Stitching Algorithms for Sub-Images of Multiple TDI CCD Chips Based on Image Matching
p.587

A Hand-Written Character Recognition Based on Feature Coding
p.594

Modified Object Tracking and Counting Method Based on Gaussian Mixture Model
p.598

Correction of CCD Camera Lens Vignetting
p.603

A Novel Multi-Planar Fusion System for PET/CT Images
p.608

Fusion Algorithm for Terahertz and Visible Light Images Based on Region Segmentation and NSCT
p.613

Research on People Counting Based on Stereo Vision
p.619

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 373-375Modified Object Tracking and Counting Method Based...

Modified Object Tracking and Counting Method Based on Gaussian Mixture Model

Abstract:

In a monocular video scene, in order to improve the efficiency of object tracking and counting under occlusion conditions. The article presents a scheme to automatically track and count people in a surveillance system. First, a modified Gaussian mixture model was employed to determine pedestrian objects from a static scene. To identify foreground objects by positions and sizes of foreground regions which were obtained. Moreover, the performance to track objects was improved by using the modified overlap tracker, the modified overlap tracker was used to analyze the centroid distance between neighboring objects and help object tracking and people counting in occlusion states of merging and splitting. On the experiments of tracking and counting people in three video sequences, the results show that the proposed method can improve the averaged detection ratio about 10% as compared to the conventional work.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 373-375)

Pages:

598-602

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.373-375.598

Citation:

Cite this paper

Online since:

August 2013

Authors:

Ming Jie Zhang, Bao Sheng Kang

Keywords:

Gaussian Mixture Model, Intelligent Surveillance System, Object Detection, Object Tracking, People Counting

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Lakshmi Devasena. C, Revathí. R : International Journal of Computer Science Issues, vol. 8(2011), p.635.

Google Scholar

[2] M. Cristani, R. Raghavendra, Del Bue. A: Neurocomputing, vol. 100(2013), p.86.

Google Scholar

[3] L. Marcenaro: Procc. of IEEE ICIP, vol. 3(2002), p.341.

Google Scholar

[4] C C. Lien , Y L. Huang, C C. Han: Procc of IEEE IIH-MSP, (2009), p.1018.

Google Scholar

[5] S. Khan, M. Shah: Proc. of Asian Conf. on Computer Vision, (2000), pp.1132-1137.

Google Scholar

[6] A. Chan, Z. Liang, Vasconcelos N: CVPR, (2008), p.1.

Google Scholar

[7] I. Haritaoglu, D. Harwood: On Pattern Analysis and Machine Intelligence, vol. 22(2000), p.809.

Google Scholar

[8] Duc. Fehr: Proceedings of AVSS, 2009：152-57.

Google Scholar

[9] A. Yilmaz, O. Javed, M. Shah: ACM Computing Surveys, vol. 38(2006), article 13.

Google Scholar

[10] C. Stauffer, W E L. Grimson: Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE Computer Society, (1999), p.246.

Google Scholar