雾天条件下，大气散射作用会减弱图像中的光照强度，导致遥感图像对比度下降，影响目标检测模型的性能。现有研究通过在有雾数据上训练模型或图像去雾预处理两种策略来应对这一问题。但在去雾过程中会导致特征丢失等问题，很难保证其与目标检测任务之间一直存在正相关性，即去雾结果有益于目标检测任务。为此，本文提出了级联学习的雾下目标检测方法(CL-FODM，Cascade Learning Foggy Object Detection Method)，建立了结合CNN和Transformer的轻量化去雾子网络，能获取更清晰的去雾特征，为下游目标检测提供更显著的语义信息。构建了特征感知引导下的多任务损失函数，在特征层面上更精准地挖掘可区分的目标语义特征，实现去雾与目标检测的协同优化，解决上下游任务间的语义不一致性问题。实验结果表明，本文提出的CL-FODM在评价指标与视觉检测效果上均优于原始模型与级联式模型。

Under foggy conditions, atmospheric scattering reduces the illumination intensity in images, which leads to a decrease in the contrast of remote sensing images and affects the performance of object detection models. Existing research has addressed this issue through two strategies: training models on foggy data or using image dehazing as a preprocessing step. However, the dehazing process can lead to feature loss, and it is difficult to ensure a consistently positive correlation between dehazing results and object detection tasks, i.e., that the dehazing results are beneficial for object detection. To address this issue, this paper proposes a Cascade Learning Foggy Object Detection Method (CL-FODM). The method establishes a lightweight dehazing sub-network combining CNN and Transformer, which can obtain clearer dehazed features and provide more salient semantic information for downstream object detection. A multi-task loss function guided by feature perception is constructed to more precisely mine discriminative target semantic features at the feature level, achieving collaborative optimization between dehazing and object detection and solving the semantic inconsistency between upstream and downstream tasks. Experimental results show that the CL-FODM proposed in this paper outperforms both the original model and the cascaded model in terms of evaluation metrics and visual detection effects.