Motion Detection Using Multiple Distributions for Background


The KIPS Transactions:PartB , Vol. 8, No. 4, pp. 381-388, Aug. 2001
10.3745/KIPSTB.2001.8.4.381,   PDF Download:

Abstract

This paper presents a motion detection algorithm that can run robustly under both indoor and outdoor environments. Motion detection based on the background extraction using temporal mean (or median) shows good performance in normal cases, but it frequently causes false alarms to ´temporal clutter´, a repetitive motion within a certain area. We developed a motion detection algorithm using multiple distributions for pixels of the background that is more robust to temporal clutter. Experimental results revealed that our approach is superior to existing methodolgies in handling various temporal clutter.


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]
T. H. Cho and Y. K. Choi, "Motion Detection Using Multiple Distributions for Background," The KIPS Transactions:PartB , vol. 8, no. 4, pp. 381-388, 2001. DOI: 10.3745/KIPSTB.2001.8.4.381.

[ACM Style]
Tai Hoon Cho and Young Kyu Choi. 2001. Motion Detection Using Multiple Distributions for Background. The KIPS Transactions:PartB , 8, 4, (2001), 381-388. DOI: 10.3745/KIPSTB.2001.8.4.381.