SoilingNet: Soiling Detection on Automotive Surround-View Cameras

Michal Uricar1, Pavel Krizek1, Ganesh Sistu2, Senthil Yogamani2

  • 1Valeo
  • 2Valeo Vision Systems


11:30 - 11:45 | Mon 28 October | The Great Room II | MoC-T3.3

Session: Regular Session on Object Detection and Classification (I)

Category: Regular Session


Cameras are an essential part of sensor suite in autonomous driving. Surround-view cameras are directly exposed to external environment and are vulnerable to get soiled. Cameras have a much higher degradation in performance due to soiling compared to other sensors. Thus it is critical to accurately detect soiling on the cameras, particularly for higher levels of autonomous driving. We created a new dataset having multiple types of soiling namely opaque and transparent. It will be released publicly as part of our WoodScape dataset cite{yogamani2019woodscape} to encourage further research. We demonstrate high accuracy using a Convolutional Neural Network (CNN) based architecture. We also show that it can be combined with the existing object detection task in a multi-task learning framework. Finally, we make use of Generative Adversarial Networks (GANs) to generate more images for data augmentation and show that it works successfully similar to the style transfer.