Presentation 1994/3/18
Moving region extraction by real-time competitive learning based on color,position,and intensity gradients,and its application
Hiroshi Arakawa, Minoru Etoh,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A region extraction method which is applicable to Man-Machine Interface is presented.Input images is divided into region fragments,using color,position,intensity gradients,and stereo difference image.And the disparity information of each regions is calculated.We realized the proposed method using pipe-line image processor(Data Cube).Experiments confirm moving object extraction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) moving images / competitive learning / stereo / segmentation
Paper # IE93-137,PRU93-144
Date of Issue

Conference Information
Committee IE
Conference Date 1994/3/18(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Moving region extraction by real-time competitive learning based on color,position,and intensity gradients,and its application
Sub Title (in English)
Keyword(1) moving images
Keyword(2) competitive learning
Keyword(3) stereo
Keyword(4) segmentation
1st Author's Name Hiroshi Arakawa
1st Author's Affiliation Central research laboratories,Matsushita Electric Industrial()
2nd Author's Name Minoru Etoh
2nd Author's Affiliation Central research laboratories,Matsushita Electric Industrial
Date 1994/3/18
Paper # IE93-137,PRU93-144
Volume (vol) vol.93
Number (no) 518
Page pp.pp.-
#Pages 8
Date of Issue