Let's Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00345651" target="_blank" >RIV/68407700:21730/21:00345651 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/WACV48630.2021.00081" target="_blank" >https://doi.org/10.1109/WACV48630.2021.00081</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV48630.2021.00081" target="_blank" >10.1109/WACV48630.2021.00081</a>

Result language

angličtina

Original language name

Let's Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving

Original language description

Wide-angle fisheye cameras are commonly used in automated driving for parking and low-speed navigation tasks. Four of such cameras form a surround-view system that provides a complete and detailed view of the vehicle. These cameras are directly exposed to harsh environmental settings and can get soiled very easily by mud, dust, water, frost. Soiling on the camera lens can severely degrade the visual perception algorithms, and a camera cleaning system triggered by a soiling detection algorithm is increasingly being deployed. While adverse weather conditions, such as rain, are getting attention recently, there is only limited work on general soiling. The main reason is the difficulty in collecting a diverse dataset as it is a relatively rare event. We propose a novel GAN based algorithm for generating unseen patterns of soiled images. Additionally, the proposed method automatically provides the corresponding soiling masks eliminating the manual annotation cost. Augmentation of the generated soiled images for training improves the accuracy of soiling detection tasks significantly by 18% demonstrating its usefulness. The manually annotated soiling dataset and the generated augmentation dataset will be made public. We demonstrate the generalization of our fisheye trained GAN model on the Cityscapes dataset. We provide an empirical evaluation of the degradation of the semantic segmentation algorithm with the soiled data.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021

ISBN

978-0-7381-4266-1

ISSN

2472-6737

e-ISSN

2642-9381

Number of pages

10

Pages from-to

766-775

Publisher name

IEEE Computer Society

Place of publication

USA

Event location

Waikoloa, HI

Event date

Jan 5, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000692171000077