Human Tracking Method Based on Maximally Stable Extremal Regions with Multi-Cameras

Li Zhang; Guo Jun Dai; Chang Jun Wang

doi:10.4028/www.scientific.net/AMM.44-47.3681

Paper Titles

Network Security Situation Prediction Using Artificial Immune System and Phase Space Reconstruction
p.3662

Research on License Plate Recognition Technology
p.3667

Order-Variable Multi-Pulses Linear Prediction Speech Coding
p.3672

The Past and Future of Phyllostachys nigra in Putuo Mountains
p.3677

Human Tracking Method Based on Maximally Stable Extremal Regions with Multi-Cameras
p.3681

The Comprehensive Evaluation of Regional Agricultural Brand Competitiveness Based on Fuzzy Gray Analysis
p.3687

An Equilibrium Principle on the AON Network for Single-Machine Scheduling Problem with Time Lags
p.3692

A Novel Efficient Mining Algorithm for Frequent Patterns on Biological Multiple Sequence
p.3697

Control of Testing Device Based on FluidSIM-P
p.3702

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 44-47Human Tracking Method Based on Maximally Stable...

Human Tracking Method Based on Maximally Stable Extremal Regions with Multi-Cameras

Abstract:

With respect to the human tracking with multi-cameras in the video surveillance system, a human tracking method based on MSER (Maximally Stable Extremal Regions) was established. The approach transforms the human tracking into elliptic region matching. The method does elliptic region fitting to each MSER, and then selects the elliptic regions which meet some constraints. These selected elliptic regions are normalized to unity circular regions. The right matched elliptic regions are gotten by rotational invariant vectors calculation, histogram density estimation and weighted average distance calculation. Experimental results show that the approach can effectively realize the human tracking with multi-cameras.

You might also be interested in these eBooks

Frontiers of Manufacturing and Design Science

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 44-47)

Pages:

3681-3686

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.44-47.3681

Citation:

Cite this paper

Online since:

December 2010

Authors:

Li Zhang, Guo Jun Dai, Chang Jun Wang

Keywords:

Human Tracking, MSER, Region Matching, Video Surveillance

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

References

[1] O. Javed, Z. Rasheed, K. Shafique and et al : Tracking Across Multiple Cameras With Disjoint Views. Proceedings of the Ninth IEEE International Conference on Computer Vision (2003), pp.952-957.

DOI: 10.1109/iccv.2003.1238451

Google Scholar

[2] S. Khan and M. Shan: Consistent Labeling of Tracked Objects in Multiple Cameras with Overlapping Fields of View. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 25 (2003), pp.1355-1360.

DOI: 10.1109/tpami.2003.1233912

Google Scholar

[3] F. Fraundorfer and H. Bischof: Evaluation of Local Detectors on Non-planar Scenes. Proceedings of the 28th Workshop of the Austrian Association for Pattern Recognition. Hagenberg (2004), pp.125-132.

Google Scholar

[4] K. Mikolajczyk, T. Tuytelaars, C. Schmid and et al: A Comparison of Affine Region Detectors. International Journal of Computer Vision Vol. 65 (2005), pp.43-72.

DOI: 10.1007/s11263-005-3848-x

Google Scholar

[5] P. Moreels and P. Perona: Evaluation of Features Detectors and Descriptors Based on 3D Objects. Proceedings of International Conference on Computer Vision. Beijing (2005), pp.800-807.

DOI: 10.1109/iccv.2005.89

Google Scholar

[6] J. Matas, O. Chum, M. Urban and et al: Robust Wide Baseline Stereo From Maximally Stable Extremal Regions. Image and Vision Computing Vol. 22 (2004), pp.761-767.

DOI: 10.1016/j.imavis.2004.02.006

Google Scholar

[7] Information on ftp: /cmp. felk. cvut. cz/pub/cmp/articles/bilek/Matas-Bilek-CVWW02. pdf.

Google Scholar

[8] J. Panero and M. Zelnik: Human dimension and interior space (Watson-Guptill Publications, USA 1979). a) b) Fig. 6 Human matching results in the left and right video images taken at the same time a-results of the first group of views, b-results of the second group of views.

Google Scholar