Feature-based speed limit sign detection using a graphics processing unit

Author

Glavtchev, Vladimir ; Muyan-Ozcelik, Pinar ; Ota, Jeffrey M. ; Owens, John D.

fYear

2011

fDate

5-9 June 2011

Firstpage

195

Lastpage

200

Abstract

In this study we test the idea of using a graphics processing unit (GPU) as an embedded co-processor for real-time detection of European Union (EU) speed-limit signs. The input to the system is a set of grayscale videos recorded from a forward-facing camera mounted in a vehicle. We introduce a new technique for implementing the radial symmetry detector (RSD) efficiently using the native rendering capabilities of a GPU. The technique maps the algorithms to the hardware such that the detection of speed-limit sign candidates is significantly accelerated. The system reaches up to 88% detection rate and runs at 33 frames per second on video sequences with VGA (640×480) resolution on an embedded system with an Intel Atom 230 @ 1.67 GHz CPU and a NVIDIA GeForce 9400M GS GPU.

Keywords

automated highways; computer graphic equipment; coprocessors; embedded systems; image colour analysis; image resolution; image sequences; object detection; rendering (computer graphics); road safety; traffic engineering computing; video cameras; video signal processing; European Union speed-limit sign; GPU; Intel Atom 230; embedded coprocessor; feature-based speed limit sign detection; forward-facing camera; graphics processing unit; grayscale video; radial symmetry detector; real-time detection; rendering; video resolution; video sequence; Graphics processing unit; Hardware; Image edge detection; Pixel; Real time systems; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium (IV), 2011 IEEE

Conference_Location

Baden-Baden

ISSN

1931-0587

Print_ISBN

978-1-4577-0890-9

Type

conf

DOI

10.1109/IVS.2011.5940539

Filename

5940539