Study of Video Object Detection and Shadow Suppression Algorithms

Abstract:

In the field of intelligent video surveillance and the multimedia applications we usually need to detect the moving object which is separated from the background. The results of the moving object detection would affect the subsequent identification, classification and tracking. Meanwhile shadow detection and suppression are also the important technology of the intelligent video surveillance. Because the moving object and shadow usually has the same behavioral characteristics, which has led to the errors of object recognition and tracking and affect the robustness of system seriously. This article studies the principle and algorithm of background subtraction, and has a detailed discussion and analysis. Shadow detection and suppression algorithms based on the YUV color space for processing. The experiment result shows that the algorithms for moving object detection with a better accuracy and stability of this paper.

• Periodical: Applied Mechanics and Materials (Volume 596)
• Pages: 374-378
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.596.374
• Online since: July 2014
• Authors: Qi Lin Gai*, Guo Qiang Wang
• Keywords: Background Subtraction, Object Detection, Shadow Inhibition, YUV Color Space

References

[1] Gavrila D, The visual analysis of human movement, Computer Vision and Image Understanding (1999), 82-98.

DOI: 10.1006/cviu.1998.0716

[2] Graham D. Finlayson, Steven D, Mark S Drew, On the Removal of Shadows from Images, IEEE Transactions on Pattern analysis and machine intelligence (2006), 158-169.

DOI: 10.1109/tpami.2006.18

[3] Cucchiara R, Prati A, Detecting moving objects, ghosts, and shadows in video Streams, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 10, 1337-1342(2003).

DOI: 10.1109/tpami.2003.1233909

[4] A. Yilmaz: Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection, Computer Vision and Pattern Recognition (2009), 345-367.

DOI: 10.1109/cvpr.2007.382987

[5] Donggyu Sim, Yongmin Kim, Detection and compression of moving objects based on new panoramic image modeling. Image and Vision Computing 27 (2009), 1527-1539.

DOI: 10.1016/j.imavis.2009.02.009