• Acta Optica Sinica
  • Vol. 29, Issue 11, 3031 (2009)
Hao Zhicheng* and Wu Chuan
Author Affiliations
  • [in Chinese]
  • show less
    DOI: 10.3788/aos20092911.3031 Cite this Article Set citation alerts
    Hao Zhicheng, Wu Chuan. Moving Object Detection from Dynamic Image Sequence Based on Stability Matrix[J]. Acta Optica Sinica, 2009, 29(11): 3031 Copy Citation Text show less

    Abstract

    To extract the moving target in video sequence fast and exactly,a self-adaptive background estimation technique was developed.Because of the different time-variability between background and foreground,a stability matrix was constructed,and according to its changes the background points could be distinguished from the foreground points.By setting two saturation values to the stability matrix,the algorithm could perceive the saltation of background automatically and update the background image quickly.Besides,in order to register the dynamic image sequences some local features were selected as templates,and projection matching technique was used to simplify the calculation and quicken the offset estimation.The experiment results show this algorithm has a high rate of convergence that only 10 frame are needed to get a stable background image,and the whole time is only 35 ms.So it meet the need of a processing ability of 25 frame/s in engineering.
    Hao Zhicheng, Wu Chuan. Moving Object Detection from Dynamic Image Sequence Based on Stability Matrix[J]. Acta Optica Sinica, 2009, 29(11): 3031
    Download Citation