Abstract
We propose a new method for background modeling. Our method is based on the two complementary approaches. One uses the probability density function (PDF) to approximatebackground model. The PDF is estimated non-parametrically by using Parzen density estimation. Then, foreground object is detected based on the estimated PDF. The method is based on the evaluation of the local texture at pixel-level resolution which reduces the effects of variations in lighting. Fusing those approachs realizes robust object detection under varying illumination. Several experiments show the effectiveness of our approach.
| Original language | English |
|---|---|
| Pages (from-to) | 21-31 |
| Number of pages | 11 |
| Journal | Progress in Informatics |
| Issue number | 7 |
| DOIs | |
| Publication status | Published - Jan 1 2010 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science(all)
- Library and Information Sciences
Cite this
Object segmentation under varying illumination : Stochastic background model considering spatial locality. / Tanaka, Tatsuya; Shimada, Atsushi; Arita, Daisaku; Taniguchi, Rin-Ichiro.
In: Progress in Informatics, No. 7, 01.01.2010, p. 21-31.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Object segmentation under varying illumination
T2 - Stochastic background model considering spatial locality
AU - Tanaka, Tatsuya
AU - Shimada, Atsushi
AU - Arita, Daisaku
AU - Taniguchi, Rin-Ichiro
PY - 2010/1/1
Y1 - 2010/1/1
N2 - We propose a new method for background modeling. Our method is based on the two complementary approaches. One uses the probability density function (PDF) to approximatebackground model. The PDF is estimated non-parametrically by using Parzen density estimation. Then, foreground object is detected based on the estimated PDF. The method is based on the evaluation of the local texture at pixel-level resolution which reduces the effects of variations in lighting. Fusing those approachs realizes robust object detection under varying illumination. Several experiments show the effectiveness of our approach.
AB - We propose a new method for background modeling. Our method is based on the two complementary approaches. One uses the probability density function (PDF) to approximatebackground model. The PDF is estimated non-parametrically by using Parzen density estimation. Then, foreground object is detected based on the estimated PDF. The method is based on the evaluation of the local texture at pixel-level resolution which reduces the effects of variations in lighting. Fusing those approachs realizes robust object detection under varying illumination. Several experiments show the effectiveness of our approach.
UR - http://www.scopus.com/inward/record.url?scp=77952899421&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77952899421&partnerID=8YFLogxK
U2 - 10.2201/NiiPi.2010.7.4
DO - 10.2201/NiiPi.2010.7.4
M3 - Article
SP - 21
EP - 31
JO - NII Journal
JF - NII Journal
SN - 1349-8614
IS - 7
ER -