RCFormer: radiation correction method for degraded multispectral UAV images using vision transformers

In modern remote sensing technology, Unmanned Aerial Vehicles (UAVs) have become crucial data acquisition platforms. However, low-altitude remote sensing images from UAVs are often affected by atmospheric scattering and absorption, particularly under conditions like haze, which severely degrade image quality. Traditional radiation correction methods cannot accurately capture the true reflectance of ground objects under these conditions. This paper introduces RCFormer, an innovative Transformer-based network architecture. It combines the self-attention mechanism of Swin Transformer with a novel network structural design, especially incorporating parallel convolutional structures to enhance the extraction capability of surface features. Additionally, with the integration of atmospheric characteristic refinement module (ACRM) and Multi-scale Feature Fusion Gate (MFFG), the proposed RCFormer not only captures atmospheric information from deep features but also effectively fuses features across different scales, thereby improving the accuracy, transferability and robustness of the radiation correction model. Finally, quantitative and qualitative evaluations using real-world data demonstrate that RCFormer outperforms other dehazing networks in both degraded and haze-free images while also offering good efficiency and ease of operation.

在现代遥感技术领域，无人机（Unmanned Aerial Vehicles, UAVs）已成为至关重要的数据采集平台。然而，无人机获取的低空遥感影像常受大气散射与吸收的影响，尤其在雾霾等天气条件下，影像质量会严重退化。传统辐射校正方法无法在这类场景下精准捕捉地物的真实反射率。本文提出RCFormer——一种基于Transformer的创新网络架构。该架构融合了Swin Transformer的自注意力机制与全新的网络结构设计，尤其引入并行卷积结构以提升地表特征的提取能力。此外，通过集成大气特征精细化模块（atmospheric characteristic refinement module, ACRM）与多尺度特征融合门控（Multi-scale Feature Fusion Gate, MFFG），所提出的RCFormer不仅能从深层特征中获取大气相关信息，还可有效实现不同尺度特征的融合，进而提升辐射校正模型的精度、迁移性与鲁棒性。最后，基于真实数据开展的定量与定性评估结果表明，RCFormer在退化影像与无雾影像上的表现均优于其他去雾网络，同时兼具良好的运行效率与易用性。

搜集汇总

背景与挑战

背景概述

该数据集提出了RCFormer方法，用于校正因大气条件（如雾霾）而退化的多光谱无人机图像。RCFormer结合了Transformer架构和并行卷积结构，通过大气特征细化模块和多尺度特征融合技术，显著提高了图像校正的准确性和鲁棒性。