Weakly Supervised Cloud Detection Combining Spectral Features and Multi-Scale Deep Network

2025-10-01

AI Summary

Weakly supervised cloud detection in optical satellite imagery is hindered by faint thin-cloud features and low-quality annotations. To address this, we propose a weakly supervised cloud detection method integrating spectral priors with a multi-scale deep network. Specifically, we design a scene-level multi-scale convolutional network incorporating a cloud thickness map to guide spectral feature modeling; further, we introduce a progressive training framework that jointly employs probability map fusion, adaptive threshold generation, and distance-weighted optimization to produce pixel-level cloud masks. Experiments on the WDCD and GF1MS-WHU datasets demonstrate that our method achieves an F1-score improvement of over 7.82% compared to state-of-the-art weakly supervised approaches, significantly enhancing robustness for thin clouds, fragmented clouds, and high-coverage clouds.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Clouds significantly affect the quality of optical satellite images, which seriously limits their precise application. Recently, deep learning has been widely applied to cloud detection and has achieved satisfactory results. However, the lack of distinctive features in thin clouds and the low quality of training samples limit the cloud detection accuracy of deep learning methods, leaving space for further improvements. In this paper, we propose a weakly supervised cloud detection method that combines spectral features and multi-scale scene-level deep network (SpecMCD) to obtain highly accurate pixel-level cloud masks. The method first utilizes a progressive training framework with a multi-scale scene-level dataset to train the multi-scale scene-level cloud detection network. Pixel-level cloud probability maps are then obtained by combining the multi-scale probability maps and cloud thickness map based on the characteristics of clouds in dense cloud coverage and large cloud-area coverage images. Finally, adaptive thresholds are generated based on the differentiated regions of the scene-level cloud masks at different scales and combined with distance-weighted optimization to obtain binary cloud masks. Two datasets, WDCD and GF1MS-WHU, comprising a total of 60 Gaofen-1 multispectral (GF1-MS) images, were used to verify the effectiveness of the proposed method. Compared to the other weakly supervised cloud detection methods such as WDCD and WSFNet, the F1-score of the proposed SpecMCD method shows an improvement of over 7.82%, highlighting the superiority and potential of the SpecMCD method for cloud detection under different cloud coverage conditions.

Problem

• Detecting thin clouds lacking distinctive spectral features
• Improving cloud detection accuracy with low-quality training samples
• Generating precise pixel-level cloud masks under varied coverage conditions

Innovation

• Weakly supervised cloud detection using spectral features
• Multi-scale deep network for scene-level cloud probability
• Adaptive thresholds with distance-weighted optimization for masks