Stereovision-based 3D obstacle detection for automotive safety driving assistance - Archive ouverte HAL Access content directly
Conference Papers Year : 2009

Stereovision-based 3D obstacle detection for automotive safety driving assistance

(1) , , , ,
1
Renaud Schmit
  • Function : Author
  • PersonId : 862242
Frédéric Pasquet
  • Function : Author
  • PersonId : 862243
Pierre-Emmanuel Viel
  • Function : Author
  • PersonId : 862244
Stéphane Guyetant
  • Function : Author
  • PersonId : 845740

Abstract

This paper describes the implementation of a real-time architecture dedicated to obstacle detection in the automotive domain, and more particularly to pre-crash situations. The method, based on stereovision, is of high complexity and can not run in real-time on standard processors. Therefore, the application is accelerated with the use of special purpose hardware; in particular, a highly parallelized disparity engine is presented. A prototype board was built, which achieves a performance of 460 GOPS and computes the application at the rate of 22 frames per second, thus reaching road safety constraints.
Not file

Dates and versions

cea-00407474 , version 1 (24-07-2009)

Identifiers

  • HAL Id : cea-00407474 , version 1

Cite

Nicolas Ventroux, Renaud Schmit, Frédéric Pasquet, Pierre-Emmanuel Viel, Stéphane Guyetant. Stereovision-based 3D obstacle detection for automotive safety driving assistance. 12th International IEEE Conference on Intelligent Transportation Systems, Oct 2009, Saint-Louis, United States. ⟨cea-00407474⟩

Collections

CEA DRT LIST
111 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More