SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection

TL;DR

SSMRadNet is a novel multi-scale state-space model for FMCW radar that achieves high efficiency and speed with significantly fewer parameters and computations while maintaining competitive segmentation and detection performance.

Contribution

It introduces the first multi-scale state-space model for radar detection and segmentation, processing raw ADC samples sequentially for improved efficiency.

Findings

10-33x fewer parameters than existing models

60-88x less computational cost (GFLOPs)

3.7x faster inference speed

Abstract

We introduce SSMRadNet, the first multi-scale State Space Model (SSM) based detector for Frequency Modulated Continuous Wave (FMCW) radar that sequentially processes raw ADC samples through two SSMs. One SSM learns a chirp-wise feature by sequentially processing samples from all receiver channels within one chirp, and a second SSM learns a representation of a frame by sequentially processing chirp-wise features. The latent representations of a radar frame are decoded to perform segmentation and detection tasks. Comprehensive evaluations on the RADIal dataset show SSMRadNet has 10-33x fewer parameters and 60-88x less computation (GFLOPs) while being 3.7x faster than state-of-the-art transformer and convolution-based radar detectors at competitive performance for segmentation tasks.