Redefining Automotive Radar Imaging: A Domain-Informed 1D Deep Learning Approach for High-Resolution and Efficient Performance
This work addresses the need for precise semantic scene interpretation in autonomous vehicles, offering a domain-specific incremental improvement.
The paper tackled the problem of insufficient spatial resolution in automotive radar imaging by redefining super-resolution as a 1D signal estimation problem, resulting in SR-SPECNet outperforming existing methods with enhanced imaging quality and resolution across varied configurations.
Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for precise semantic scene interpretation. Classical super-resolution techniques adapted from optical imaging inadequately address the distinct characteristics of radar signal data. In response, our study redefines radar imaging super-resolution as a one-dimensional (1D) signal super-resolution spectra estimation problem by harnessing the radar signal processing domain knowledge, introducing innovative data normalization and a domain-informed signal-to-noise ratio (SNR)-guided loss function. Our tailored deep learning network for automotive radar imaging exhibits remarkable scalability, parameter efficiency and fast inference speed, alongside enhanced performance in terms of radar imaging quality and resolution. Extensive testing confirms that our SR-SPECNet sets a new benchmark in producing high-resolution radar range-azimuth images, outperforming existing methods across varied antenna configurations and dataset sizes. Source code and new radar dataset will be made publicly available online.