UCloudNet用残差+深度监督提升云图分割精度，训练更快更省资源。
UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation
- 在编码器中加入残差连接，增强特征提取能力。
- 相比以往方法，分割准确率更高，训练耗时更少。
- 适合实时云监测系统，尤其适用于地面摄像头场景。
近年来，气象学中开始使用地面天空摄像机进行云层观测。分析这些摄像机图像有助于计算云覆盖率并理解大气现象。传统上，云图像分割依赖于常规计算机视觉技术。随着深度学习的发展，卷积神经网络（CNN）被越来越多地应用于该任务。尽管效果良好，但CNN通常需要大量训练轮次才能收敛，给天空摄像机系统的实时处理带来挑战。本文提出一种带有深度监督的残差U-Net（UCloudNet），在保持更高分割精度的同时显著降低训练开销。通过在UCloudNet的编码器中引入残差连接，进一步提升了特征提取能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。