Log In Sign Up

Let's Get Dirty: GAN Based Data Augmentation for Soiling and Adverse Weather Classification in Autonomous Driving

by   Michal Uricar, et al.

Cameras are getting more and more important in autonomous driving. Wide-angle fisheye cameras are relatively cheap sensors and very suitable for automated parking and low-speed navigation tasks. Four of such cameras form a surround-view system that provides a complete and detailed view around the vehicle. These cameras are usually directly exposed to harsh environmental settings and therefore can get soiled very easily by mud, dust, water, frost, etc. The soiling on the camera lens has a direct impact on the further processing of the images they provide. While adverse weather conditions, such as rain, are getting attention recently, there is limited work on lens soiling. We believe that one of the reasons is that it is difficult to build a diverse dataset for this task, which is moreover expensive to annotate. We propose a novel GAN based algorithm for generating artificial soiling data along with the corresponding annotation masks. The manually annotated soiling dataset and the generated augmentation dataset will be made public. We demonstrate the generalization of our fisheye trained soiling GAN model on the Cityscapes dataset. Additionally, we provide an empirical evaluation of the degradation of the semantic segmentation algorithm with the soiled data.


page 2

page 4

page 6

page 7

page 8

page 12

page 14

page 15


SoilingNet: Soiling Detection on Automotive Surround-View Cameras

Cameras are an essential part of sensor suite in autonomous driving. Sur...

Canadian Adverse Driving Conditions Dataset

The Canadian Adverse Driving Conditions (CADC) dataset was collected wit...

Raindrops on Windshield: Dataset and Lightweight Gradient-Based Detection Algorithm

Autonomous vehicles use cameras as one of the primary sources of informa...

Universal Semantic Segmentation for Fisheye Urban Driving Images

Semantic segmentation is a critical method in the field of autonomous dr...

Fisheye Lens Camera based Autonomous Valet Parking System

This paper proposes an efficient autonomous valet parking system utilizi...

CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations

High quality perception is essential for autonomous driving (AD) systems...

SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving

Surround-view cameras are a primary sensor for automated driving, used f...