A Novel Approach in Video Scene Background Estimation
Author:
, , , , ,Year
: 2010
Abstract: Abstract—This paper presents a novel method for
background estimation in a video sequence from the function
estimation point of view. The proposed algorithm, called
Kernel-based Background Learning (KBL), is designed based
on kernel machine joint with learning schemes. In order to
estimate background using KBL algorithm, we first interpret
foreground samples as outliers relative to the background ones
and so propose an Outlier Separator (OS). Then, the obtained
results of OS algorithm are employed in the KBL method in
order to train and estimate background in each pixel.
Experimental results show the high accuracy and effectiveness
of the proposed method in background estimation and
foreground detection for the scenes including moving
backgrounds, camera shakes, and non-empty backgrounds.
background estimation in a video sequence from the function
estimation point of view. The proposed algorithm, called
Kernel-based Background Learning (KBL), is designed based
on kernel machine joint with learning schemes. In order to
estimate background using KBL algorithm, we first interpret
foreground samples as outliers relative to the background ones
and so propose an Outlier Separator (OS). Then, the obtained
results of OS algorithm are employed in the KBL method in
order to train and estimate background in each pixel.
Experimental results show the high accuracy and effectiveness
of the proposed method in background estimation and
foreground detection for the scenes including moving
backgrounds, camera shakes, and non-empty backgrounds.
Keyword(s): Index Terms—Background estimation,outlier separator,
kernel-based background learning
Collections
:
-
Statistics
A Novel Approach in Video Scene Background Estimation
Show full item record
| contributor author | حمیدرضا برادران کاشانی | en |
| contributor author | سیدعلی رضا سیدین | en |
| contributor author | هادی صدوقی یزدی | en |
| contributor author | Hamidreza Baradaran Kashani | fa |
| contributor author | Seyed Alireza Seyedin | fa |
| contributor author | Hadi Sadoghi Yazdi | fa |
| date accessioned | 2020-06-06T14:33:49Z | |
| date available | 2020-06-06T14:33:49Z | |
| date issued | 2010 | |
| identifier uri | https://libsearch.um.ac.ir:443/fum/handle/fum/3402007 | |
| description abstract | Abstract—This paper presents a novel method for background estimation in a video sequence from the function estimation point of view. The proposed algorithm, called Kernel-based Background Learning (KBL), is designed based on kernel machine joint with learning schemes. In order to estimate background using KBL algorithm, we first interpret foreground samples as outliers relative to the background ones and so propose an Outlier Separator (OS). Then, the obtained results of OS algorithm are employed in the KBL method in order to train and estimate background in each pixel. Experimental results show the high accuracy and effectiveness of the proposed method in background estimation and foreground detection for the scenes including moving backgrounds, camera shakes, and non-empty backgrounds. | en |
| language | English | |
| title | A Novel Approach in Video Scene Background Estimation | en |
| type | Journal Paper | |
| contenttype | External Fulltext | |
| subject keywords | Index Terms—Background estimation | en |
| subject keywords | outlier separator | en |
| subject keywords | kernel-based background learning | en |
| journal title | International Journal of Computer Theory and Engineering | fa |
| pages | 274-282 | |
| journal volume | 2 | |
| journal issue | 2 | |
| identifier link | https://profdoc.um.ac.ir/paper-abstract-1019359.html | |
| identifier articleid | 1019359 |