UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation
This work addresses real-time processing challenges in sky camera systems for cloud observation, representing an incremental improvement in domain-specific deep learning applications.
The paper tackles cloud image segmentation for meteorology by introducing UCloudNet, a residual U-Net with deep supervision, which achieves better accuracy and reduces training consumption compared to previous methods.
Recent advancements in meteorology involve the use of ground-based sky cameras for cloud observation. Analyzing images from these cameras helps in calculating cloud coverage and understanding atmospheric phenomena. Traditionally, cloud image segmentation relied on conventional computer vision techniques. However, with the advent of deep learning, convolutional neural networks (CNNs) are increasingly applied for this purpose. Despite their effectiveness, CNNs often require many epochs to converge, posing challenges for real-time processing in sky camera systems. In this paper, we introduce a residual U-Net with deep supervision for cloud segmentation which provides better accuracy than previous approaches, and with less training consumption. By utilizing residual connection in encoders of UCloudNet, the feature extraction ability is further improved.