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

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.