Presentation 2012-02-10
Evaluation of Case-Based Background Model
Yosuke NONAKA, Atsushi SHIMADA, Hajime NAGAHARA, Rin-ichiro TANIGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Background subtraction is one of the important techniques for object detection. In general, there is a trade-off problem between accuracy and a computational cost. A new framework called "Case-Based Background Modeling '' has been proposed to tackle this issue. This method keeps practical models only to reduce a memory usage and a computational cost. Meanwhile, it selects effective image features to enhance accuracy. According to preliminary research, it is known that the performance of the framework is affected by the design of image features. In this paper, we examine a performance in detail with many kinds of datasets including various background changes. Our experimental results support to find out the most effective usage of Case-Based Background Model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Background Model / Case-Based Method / Object detection / Evaluation
Paper # PRMU2011-226,SP2011-141
Date of Issue

Conference Information
Committee SP
Conference Date 2012/2/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluation of Case-Based Background Model
Sub Title (in English)
Keyword(1) Background Model
Keyword(2) Case-Based Method
Keyword(3) Object detection
Keyword(4) Evaluation
1st Author's Name Yosuke NONAKA
1st Author's Affiliation Department of Electrical Engineering and Computer Science, School of Engineering, Kyushu University()
2nd Author's Name Atsushi SHIMADA
2nd Author's Affiliation Graduate School of Information Science and Electrical Engineering, Kyushu University
3rd Author's Name Hajime NAGAHARA
3rd Author's Affiliation Graduate School of Information Science and Electrical Engineering, Kyushu University
4th Author's Name Rin-ichiro TANIGUCHI
4th Author's Affiliation Graduate School of Information Science and Electrical Engineering, Kyushu University
Date 2012-02-10
Paper # PRMU2011-226,SP2011-141
Volume (vol) vol.111
Number (no) 431
Page pp.pp.-
#Pages 6
Date of Issue