22 November 2016 Moving object detection using a background modeling based on entropy theory and quad-tree decomposition
Author Affiliations +
J. of Electronic Imaging, 25(6), 061615 (2016). doi:10.1117/1.JEI.25.6.061615
A particular algorithm for moving object detection using a background subtraction approach is proposed. We generate the background model by combining quad-tree decomposition with entropy theory. In general, many background subtraction approaches are sensitive to sudden illumination change in the scene and cannot update the background image in scenes. The proposed background modeling approach analyzes the illumination change problem. After performing the background subtraction based on the proposed background model, the moving targets can be accurately detected at each frame of the image sequence. In order to produce high accuracy for the motion detection, the binary motion mask can be computed by the proposed threshold function. The experimental analysis based on statistical measurements proves the efficiency of our proposed method in terms of quality and quantity. And it even outperforms substantially existing methods by perceptional evaluation.
© 2016 SPIE and IS&T
Omar Elharrouss, Driss Moujahid, Samah Elkah, Hamid Tairi, "Moving object detection using a background modeling based on entropy theory and quad-tree decomposition," Journal of Electronic Imaging 25(6), 061615 (22 November 2016). https://doi.org/10.1117/1.JEI.25.6.061615


Abnormal behaviors detection using particle motion model
Proceedings of SPIE (March 04 2015)
Behavior subtraction
Proceedings of SPIE (January 28 2008)
Salient region detection for object tracking
Proceedings of SPIE (May 08 2012)
Object tracking and classification in aerial videos
Proceedings of SPIE (April 14 2008)

Back to Top