4DR P2T: 4D Radar Tensor Synthesis with Point Clouds

TL;DR

This paper introduces 4DR P2T, a novel 4D Radar tensor synthesis method using a cGAN that improves point cloud data quality for deep learning, validated on the K-Radar dataset.

Contribution

The paper presents a new 4D Radar tensor generation model employing a cGAN, enhancing data quality and measurement efficiency for deep learning applications.

Findings

Achieved an average PSNR of 30.39dB and SSIM of 0.96 on K-Radar dataset.

Identified the 5% percentile method as best for overall performance.

The 1% percentile method balances data reduction and performance.

Abstract

In four-dimensional (4D) Radar-based point cloud generation, clutter removal is commonly performed using the constant false alarm rate (CFAR) algorithm. However, CFAR may not fully capture the spatial characteristics of objects. To address limitation, this paper proposes the 4D Radar Point-to-Tensor (4DR P2T) model, which generates tensor data suitable for deep learning applications while minimizing measurement loss. Our method employs a conditional generative adversarial network (cGAN), modified to effectively process 4D Radar point cloud data and generate tensor data. Experimental results on the K-Radar dataset validate the effectiveness of the 4DR P2T model, achieving an average PSNR of 30.39dB and SSIM of 0.96. Additionally, our analysis of different point cloud generation methods highlights that the 5% percentile method provides the best overall performance, while the 1% percentile method optimally balances data volume reduction and performance, making it well-suited for deep learning applications.