A Real Implementation of Dangerous Objects Capturing in Surveillance Web

Yun Cheng; Hai Tao Lang; Peng Yao; Rui Guo; Jian Ying Hu; Jie Wang

doi:10.4028/www.scientific.net/AMM.278-280.1032

Paper Titles

The Design of Smart Meter for Civil Airports Covered Bridge Equipment Based on ATT7022A
p.1011

Analysis on the Condition of the Electric Energy Metering Device and the Strategy of Inspection
p.1015

Design of a Direct TPMS System Based on SP37
p.1022

Rolling Bearing Fault Diagnosis Using Sample Entropy and 1.5 Dimension Spectrum Based on EMD
p.1027

A Real Implementation of Dangerous Objects Capturing in Surveillance Web
p.1032

Contactless Power Supply System Design Based on DSP
p.1039

High-Performance Real-Time Bus in Parallel Processing System
p.1043

Performance on OCDMA Encoder Based on Photonic Crystal
p.1047

The NC Power Supply Design of Large Current and Wide Frequency Pulse in Short Electric Arc Machining
p.1051

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280A Real Implementation of Dangerous Objects...

A Real Implementation of Dangerous Objects Capturing in Surveillance Web

Abstract:

The main focus of our research is capturing dangerous objects when they appear under the surveillance camera again, while have performed a dangerous activities in other places. Our solution is a two-phase method, including object learning and capturing under the classification framework. The samples of objects and non-objects are collected to train a classifier with libSVM in object learning phase. In object capturing phase, all moving objects are detected by background subtraction, then are classified into dangerous or non-dangerous. To obtain a robust objects representation to illumination, scale, rotation etc. we fuse HSV space based color feature and multiple scale texture feature. The experimental results with real surveillance data validated the proposed method.

You might also be interested in these eBooks

Advances in Mechatronics and Control Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 278-280)

Pages:

1032-1035

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.278-280.1032

Citation:

Cite this paper

Online since:

January 2013

Authors:

Yun Cheng, Hai Tao Lang, Peng Yao, Rui Guo, Jian Ying Hu, Jie Wang

Keywords:

Bag of Features, Object Classification, Object Recognition, Surveillance

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Fieguth, P. and Terzopoulos, D., Color-based tracking of heads and other mobile objects at video frame rates,. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). p.21–27. (1996).

DOI: 10.1109/cvpr.1997.609292

Google Scholar

[2] Comaniciu, D., Ramesh, V., Andmeer, P., Kernel-based object tracking,. IEEE Trans. Patt. Analy. Mach. Intell. (PAMI), 25, p.564–575. (2003).

DOI: 10.1109/tpami.2003.1195991

Google Scholar

[3] T. Joshi, B. Vijayakumar, D. Kriegman, and J. Ponce, HOT curves for modelling and recognition of smooth curved 3D objects, Image Vision Comput. 15, p.479–498, (1997).

DOI: 10.1016/s0262-8856(97)00001-2

Google Scholar

[4] Peng Yao, Yongtian Wang, et. al, Dangerous Object Recognition for Visual Surveillance, ICALIP, pp.55-61, (2012).

Google Scholar

[5] C. Stauffer and W. Grimson, Adaptive background mixture models for real-time tracking, in Proc. IEEE Conf. Computer Vision and Pattern Recognition(CVPR), vol. 2, p.246–252, (1999).

DOI: 10.1109/cvpr.1999.784637

Google Scholar