用扩散模型提升雷达多普勒分辨率，更好分离慢速目标
Enhancing Fourier-based Doppler Resolution with Diffusion Models
- 基于零填充FFT结果，用扩散模型进行生成式精修
- 可有效分离距离近的多个目标，突破传统FFT极限
- 适合雷达信号处理、低速目标检测等场景
在雷达系统中，多普勒维的高分辨率对于探测慢速运动目标至关重要，能更清晰地区分目标与杂波（如静止物体）。然而，受硬件能力和物理因素限制，实际分辨率常不足。为此，本文提出一种基于人工智能的方法，通过生成式神经网络——扩散模型，对零填充快速傅里叶变换（zero-padded FFT）生成的时域-多普勒图进行精修，从而提升多普勒分辨率。实验表明，该方法可有效分离距离过近的目标，克服传统FFT的分辨率瓶颈。
原文摘要 · Abstract (English)
In radar systems, high resolution in the Doppler dimension is important for detecting slow-moving targets as it allows for more distinct separation between these targets and clutter, or stationary objects. However, achieving sufficient resolution is constrained by hardware capabilities and physical factors, leading to the development of processing techniques to enhance the resolution after acquisition. In this work, we leverage artificial intelligence to increase the Doppler resolution in range-Doppler maps. Based on a zero-padded FFT, a refinement via the generative neural networks of diffusion models is achieved. We demonstrate that our method overcomes the limitations of traditional FFT, generating data where closely spaced targets are effectively separated.
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。