SoilingNet:車載サラウンドビューカメラの汚れ検出
SoilingNet: Soiling Detection on Automotive Surround-View Cameras
自動運転車のサラウンドビューカメラに付着する不透明・透明な汚れを検出するCNNベース手法を提案し、物体検出とのマルチタスク学習やGANによるデータ拡張の有効性も示した研究。
著者: Michal Uricar, Pavel Krizek, Ganesh Sistu, Senthil Yogamani
分類: cs.CV, cs.AI, cs.LG, cs.RO, stat.ML
原文アブストラクト
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.
