Background Generation using Temporal and Spatial Information of Pixels


The KIPS Transactions:PartB , Vol. 17, No. 1, pp. 15-22, Feb. 2010
10.3745/KIPSTB.2010.17.1.15,   PDF Download:

Abstract

Background generation is very important for accurate object tracking in video surveillance systems. Traditional background generation techniques have some problems with non-moving objects for longer periods. To overcome this problem, we propose a newbackground generation method using mean-shift and Fast Marching Method (FMM) to use pixel information along temporal and spatial dimensions. The mode of pixel value density along time axis is estimated by mean-shift algorithm and spatial information is evaluated by FMM, and then they are used together to generate a desirable background in the existence of non-moving objects during longer period. Experimental results show that our proposed method is more efficient than the traditional method.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. H. Cho and H. B. Kang, "Background Generation using Temporal and Spatial Information of Pixels," The KIPS Transactions:PartB , vol. 17, no. 1, pp. 15-22, 2010. DOI: 10.3745/KIPSTB.2010.17.1.15.

[ACM Style]
Sang Hyun Cho and Hang Bong Kang. 2010. Background Generation using Temporal and Spatial Information of Pixels. The KIPS Transactions:PartB , 17, 1, (2010), 15-22. DOI: 10.3745/KIPSTB.2010.17.1.15.