Object Detection based Weighted-Center Surround Difference

Intelligent traffic surveillance technology is an issue in the field of traffic data analysis. Therefore, we need the technology to detect moving objects in real-time while there are variations in background and natural light. In this paper, we proposed a Weighted-Center Surround Difference method for object detection in outdoor environments. The proposed system detects objects using the saliency map that is obtained by analyzing the weight of each layers of Gaussian pyramid. In order to validate the effectiveness of our system, we implemented the proposed method using a digital signal processor, TMS320DM6437. Experimental results show that blurred noisy around objects was effectively eliminated and the object detection accuracy is improved.

Authors:

• Seung-Hun Kim
• Kye-Hoon Jeon
• Byoung-Doo Kang
• I1-Kyun Jung

Keywords:

• Saliency Map
• Center Surround Difference
• Object Detection
• Surveillance System

References:

[1] U. Lee, Y. Kim, S. Lee, and H. Choi, "DSP-based real-time moving
object detection and tracking", Korea Journal of Signal Processing
Systems, No. 11, No. 4, 263-269, 2010.
[2] . Jing, D. Rajan, and C.H. Siong, "Motion Detection with Adaptive
Background and Dynamic Thresholds", Proc. Information,
Communications and Signal Processing, pp. 41-45, 2005.
[3] J. Jeon, J. Lim, J. Kim, S. Kim, and B. Kang, "Eigen-background and
object detection systems using Clustering," Journal of Korea Multimedia
Society, No. 13, No. 1, p. 47-57, 2010.
[4] R. Li, Y. Chen, and X. Zhang, "Fast Robust Eigen-Background Updating
for Foreground Detection", Proc. ICIP 2006, pp.1833-1836, 2006.
[5] S.C. Cheung and C. Kamath, "Robust techniques for background
subtraction in urban traffic video", Proc. SPIE, Vol. 5308, pp.881-892,
2004.
[6] Q. Zang, R. Klette, "Robust Background Subtraction and Maintenance",
Proc. Int-l Conf. Pattern Recognition, Vol. 2, pp.90-93, 2004.
[7] J.W. Woo, W.N. Lee, and M.H Lee, "A Traffic Surveillance System
Using Dynamic Saliency Map and SVM Boosting", Int. J. Control,
Automation and Systems, Vol. 8, No. 5, pp.948-956, 2010.