Rainy weather recognition from in-vehicle camera images for driver assistance

Author

Kurihata, Hiroyuki ; Takahashi, Tomokazu ; Ide, Ichiro ; Mekada, Yoshito ; Murase, Hiroshi ; Tamatsu, Yukimasa ; Miyahara, Takayuki

Author_Institution

Graduate Sch. of Inf. Sci., Nagoya Univ., Japan

fYear

2005

fDate

6-8 June 2005

Firstpage

205

Lastpage

210

Abstract

We propose a weather recognition method from in-vehicle camera images that uses a subspace method to judge rainy weather by detecting raindrops on the windshield. "Eigendrops" represent the principal components extracted from raindrop images in the learning stage. Then the method detects raindrops by template matching. In experiments using actual video sequences, our method showed good detection ability of raindrops and promising results for rainfall judgment from detection results.

Keywords

cameras; driver information systems; feature extraction; image matching; image representation; image sequences; learning (artificial intelligence); rain; video signal processing; driver assistance; eigendrops; in-vehicle camera image; rainfall judgment; rainy weather recognition; subspace method; template matching; video sequences; windshield; Automotive components; Cameras; Feature extraction; Image processing; Image recognition; Image sensors; Pattern recognition; Rain; Roads; Sensor systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium, 2005. Proceedings. IEEE

Print_ISBN

0-7803-8961-1

Type

conf

DOI

10.1109/IVS.2005.1505103

Filename

1505103