Human Verification in a Video Surveillance System Using Statistical Features

A human verification system is presented in this paper. The system consists of several steps: background subtraction, thresholding, line connection, region growing, morphlogy, star skelatonization, feature extraction, feature matching, and decision making. The proposed system combines an advantage of star skeletonization and simple statistic features. A correlation matching and probability voting have been used for verification, followed by a logical operation in a decision making stage. The proposed system uses small number of features and the system reliability is convincing.

Authors:

• Sanpachai Huvanandana

Keywords:

• Human verification
• object recognition
• videounderstanding
• segmentation.

References:

[1] Akira U. and Nobuji T., "Human Detection using Geometrical Pixel
Value Structure", IEEE Internation Conference on Automatic Face and
Gesture Recognition, FGR-02, 2002.
[2] Borghys, D. , Verlinde, P., Perneel, C. , Acheroy, M. , "Multi-level Data
Fusion for the Detection of Targets using Multi-Spectral Image
Sequences", Opt. Eng., Vol. 37, No. 2, pp. 477-484, February 1998.
[3] [3a] Chen X, He Z, Anderson D, Keller J & Skubic M, "Adaptive
Silhouette Extraction and Human Tracking in Complex and Dynamic
Environments", International Conference on Image Processing, Atlanta,
Georgia, October 8-13, 2006.
[4] Constantine P., Theodoros E., and Tomaso P., "A trainable pedestrian
detection system", In Proc. of Intelliggent Vehicles, pages 241-246,
1998.
[5] Elgammal A., Harwood D., and Davis L.S., "Non-Parametric Model for
Background Subtraction.", International Proc. IEEE ICCV-99 Frame-
Rate Workshop, 1999.
[6] Fengliang Xu, Kikuo Fujimura," Human Detection Using Depth and
Gray Images.",IEEE Conference on Advanced Video and Signal Based
Surveillance (AVSS- 03 ), 2003.
[7] Grimson W. E. L. and Stauffer C., "Adaptive Background Mixture
Models for Real-time Tracking.", Proc. IEEE Conference CVPR, Vol. 1
,pp.22-29, 1999.
[8] Haritaoglu I., Harwood D., and Davis L.S., "W4: Real-Time System for
Detection and Tracking People in 2 › D.", 5th European Conference on
Computer Vision, 1998.
[9] Hironobu Fujiyoshi and Alan J. Lipton, "Real-time Human Motion
Ananlysis by Image Skeletonization", IEICE Transanction on
Information & System, vol.E87-D, No.1, 2004.
[10] Jianpeng Z. and Jack H., "Real Time Robust Human Detection and
Tracking System", Proceeding of 2005 IEEE Computer Society
Conference on Computer Vision and Pattern Recognition workshop
(CVPR-05), Vol.3.
[11] Oliver N., B. Rosario, and A. Pentland, "A Baysian Computer Vision
System for Modeling Human Interactions.", International Conference on
Vision System, 1999.
[12] Rafael C. Gonzalez and Richard E. Woods, "Digital Image Processing",
Prentice Hall, 2002.
[13] Rosin, P.L. , Ellis, T. , "Image Difference Threshold Strategies and
Shadow Detection", British Machine Vision Conf., pp. 347-356, 1995.
[14] Wren C.R., Azarbayejani A., Darrell T., and Pentland A., "Pfinder: Realtime
Tracking of Human Body.", IEEE Trans. Pattern Analysis and
Machine Intelligence, Vol. 19, No.7, pp.780-785, July 1997.
[15] Wu B. and Nevatia R, "Detection of Multiple, Partially Occluded
Humans in a Single Image by Basian Combination of Edgelet Part
Detectors" ICCV-05, 2005.