Detection of Raindrop with Various Shapes on aWindshield
Year: 2016
Type: conference-paper
Abstract: This paper presents the method to detect raindrops with various shapes on a windshield from an in-vehicle single camera. Raindrops on a windshield causes various bad influence for video-based automobile applications, such as pedestrian detection, lane detection and so on. Therefore, it’s important to understand the state of the raindrop on a windshield for a driving safety support system or an automatic driving vehicle. Although conventional methods are considered on isolated spherical raindrops, our method can be applied to raindrops with various shapes, e.g. a band-like shape. In the daytime, our method detects raindrop candidates by examining the difference of the blur between the surrounding areas. We uses the ratio of the edge strength extracted from two kinds of smoothed images as the degree of the blur. At night, bright areas whose intensity does not change so much are detected as raindrops.
Authors: Junki Ishizuka, Kazunori Onoguchi
Institution: Hirosaki University
Language: English
Subfield: Automotive Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2344811863