Presentation 2005-09-22
Eliminating Occluded Areas for Planar Projection Stereopsis Method
Kazunori ONOGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The planar projection stereopsis method detects objects whose heights are different from the road plane by projective transformation between stereo images. This method detects not only objects but also road areas occluded by objects in one image. If the baseline of stereo cameras is short, this is not a problem because occluded areas are small. However, in the case that the baseline is long, it is difficult to detect objects' areas exactly because occluded areas are larger than objects' areas. This paper presents a method for eliminating occluded areas, comparing contours of areas detected by the planar projection stereopsis method with edges in an original image. An experiment was conducted to determine the efficacy for detecting pedestrians and vehicles in stereo images obtained from cameras set on both sides of the footbridge over a road with four lanes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stereo / Planar Projection / Occluded Area / Projective Transformation / Video Surveillance
Paper # NLC2005-43,PRMU2005-70
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/9/15(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Eliminating Occluded Areas for Planar Projection Stereopsis Method
Sub Title (in English)
Keyword(1) Stereo
Keyword(2) Planar Projection
Keyword(3) Occluded Area
Keyword(4) Projective Transformation
Keyword(5) Video Surveillance
1st Author's Name Kazunori ONOGUCHI
1st Author's Affiliation Faculty of Science and Technology, Hirosaki University()
Date 2005-09-22
Paper # NLC2005-43,PRMU2005-70
Volume (vol) vol.105
Number (no) 302
Page pp.pp.-
#Pages 6
Date of Issue