SoilingNet: Soiling Detection on Automotive Surround-View Cameras
This addresses the issue of camera performance degradation due to soiling for autonomous driving systems, but it is incremental as it builds on existing methods like CNNs and GANs.
The paper tackles the problem of detecting soiling on automotive surround-view cameras, which is critical for autonomous driving, by creating a new dataset with multiple soiling types and demonstrating high accuracy using a CNN-based architecture, combined with multi-task learning and GAN-based data augmentation.
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.