Presentation 2013-12-12
Proposal of obstacle detector which involves learning system while driving
Hiroki KURATA, Hirokazu MATSUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we propose a method that detects far obstacles for a vehicle by using a monocular camera. The method learns the far obstacle detection by using the driving situation that a vehicle comes to near the objects on the front of the vehicle by each image frame. This method classifies an image into road region and non-road region by wavelet transform. Near objects can be 3-D reconstructed by the disparities of textures caused by the camera motion. Far objects cannot be 3-D reconstructed, since they have too small disparities. But, the far objects become near objects by vehicle motion. Therefore, we learn that 3-D objects have what kinds of texture in the far region, that are recognized as obstacles in the near region.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Monocular Camera / Far Obstacle Recognition / Wavelet Transformation / Learning
Paper # PRMU2013-68
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/12/5(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) Proposal of obstacle detector which involves learning system while driving
Sub Title (in English)
Keyword(1) Monocular Camera
Keyword(2) Far Obstacle Recognition
Keyword(3) Wavelet Transformation
Keyword(4) Learning
1st Author's Name Hiroki KURATA
1st Author's Affiliation Graduate School of Engineering, Mie University()
2nd Author's Name Hirokazu MATSUI
2nd Author's Affiliation Graduate School of Engineering, Mie University
Date 2013-12-12
Paper # PRMU2013-68
Volume (vol) vol.113
Number (no) 346
Page pp.pp.-
#Pages 4
Date of Issue