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

Author

Ventroux, Nicolas ; Schmit, Renaud ; Pasquet, Frédéric ; Viel, Pierre-Emmanuel ; Guyetant, Stéphane

Author_Institution

Embedded Comput. Lab., CEA LIST, Gif-sur-Yvette, France

fYear

2009

fDate

4-7 Oct. 2009

Firstpage

1

Lastpage

6

Abstract

This paper describes the implementation of a realtime 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.

Keywords

automobiles; object detection; road safety; stereo image processing; traffic engineering computing; automotive safety driving assistance; parallelized disparity engine; processor; road safety constraints; stereo vision-based 3D obstacle detection; Automotive engineering; Computer architecture; Engines; Hardware; Image sensors; Intelligent transportation systems; Layout; Prototypes; Roads; Safety;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems, 2009. ITSC '09. 12th International IEEE Conference on

Conference_Location

St. Louis, MO

Print_ISBN

978-1-4244-5519-5

Electronic_ISBN

978-1-4244-5520-1

Type

conf

DOI

10.1109/ITSC.2009.5309832

Filename

5309832