Presentation 2009-05-28
Coupled Object Detection and Sparse Depth Estimation
Yu Wang, Jien Kato, Toyohide Watanabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Detecting and localizing other traffic participants, such as pedestrians and vehicles, from a moving vehicle has various applications in smart vehicle. In this work, we address such a problem by utilizing image sensors, namely stereo cameras mounted on the vehicle. Our proposed method integrates appearance based object detection and sparse depth estimation in a novel fashion. With depth estimation, we transform the prior distribution of objects' actual size into the distribution of their imaged size to improve the detection performance. By contrast, we use depth information that contributed to correct object hypotheses to better localize objects. Being different with many previous works, we take the trade-off between accuracy and computational cost in the first place of consideration, and try to make the most efficient integration for onboard applications.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object detection / depth estimation / feature matching / driver assistance
Paper # IE2009-24,PRMU2009-15,MI2009-15
Date of Issue

Conference Information
Committee IE
Conference Date 2009/5/21(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Coupled Object Detection and Sparse Depth Estimation
Sub Title (in English)
Keyword(1) object detection
Keyword(2) depth estimation
Keyword(3) feature matching
Keyword(4) driver assistance
1st Author's Name Yu Wang
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Jien Kato
2nd Author's Affiliation Graduate School of Information Science, Nagoya University
3rd Author's Name Toyohide Watanabe
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2009-05-28
Paper # IE2009-24,PRMU2009-15,MI2009-15
Volume (vol) vol.109
Number (no) 63
Page pp.pp.-
#Pages 4
Date of Issue