Radio frequency interference (RFI) is a significant threat to accurate microwave remote sensing. The RFI signals manifest themselves in unpredictable locations and patterns in the image, which will cause measurement distortion and image degradation or even lead to wrong retrievals of the geophysical parameters. Accurate detection of RFI artifacts is a prerequisite step to preserve the overall quality of remote sensing quality. In this article, a semantic cognitive enhancement network for RFI signature detection is proposed. It employs an encoder–decoder architecture, which incorporates the atrous spatial pyramid pooling, depthwise convolution, and self-attentional mechanism. Rather than detecting the existence of RFI artifacts for an entire image, the proposed scheme can realize RFI recognition in a pixelwise manner without setting predefined thresholds. Extensive experimental results on diverse scenarios in Sentinel-1 images with various RFI types are provided, which demonstrates robust detection performance for both strong and weak interference without requiring a large number of training samples.

中文翻译：

---

使用语义认知增强网络的雷达遥感图像射频干扰特征检测


射频干扰（RFI）是精确微波遥感的重大威胁。 RFI信号在图像中以不可预测的位置和模式显现，这将导致测量失真和图像质量下降，甚至导致地球物理参数的错误检索。准确检测 RFI 伪影是保持遥感质量整体质量的先决条件。本文提出了一种用于 RFI 签名检测的语义认知增强网络。它采用编码器-解码器架构，结合了多孔空间金字塔池、深度卷积和自注意力机制。所提出的方案不是检测整个图像是否存在 RFI 伪影，而是可以以像素方式实现 RFI 识别，而无需设置预定义阈值。提供了在具有各种 RFI 类型的 Sentinel-1 图像中的不同场景下的广泛实验结果，这表明在不需要大量训练样本的情况下，对强干扰和弱干扰都有鲁棒的检测性能。