面向自动驾驶感知系统的精度与实时感知的四维雷达预处理
Accuracy- and Real-Time-Aware 4D Radar Preprocessing for Autonomous Driving Perception Systems
浏览论文内容
中文总结 AI 辅助
本文提出一种四维雷达预处理框架，通过P3DP提取点云、MF-KDE增强稀疏点云、ENS评估嵌入式部署，兼顾精度、实时性与复杂度，提升恶劣天气下三维目标检测性能。
中文摘要 AI 辅助
四维雷达因其在恶劣天气条件下的稳定感知能力，已成为提升自动驾驶感知系统鲁棒性的有前景的下一代传感器。然而，在硬件资源受限的嵌入式环境中部署四维雷达，需要雷达表示预处理，该预处理需同时考虑感知精度、实时性能和计算复杂度。本文提出了一种基于四维雷达的三维目标检测预处理框架。首先，基于百分位数的三维形状保持（P3DP）从雷达张量中提取点云，同时保留物体形状信息并抑制噪声和虚警。其次，基于多帧的核密度估计噪声点判别（MF-KDE）提高了稀疏雷达点云的密度和可靠性。最后，嵌入式与净得分（ENS）通过联合考虑精度、实时性能、恶劣天气鲁棒性和模型复杂度来评估嵌入式部署的适用性。
英文摘要
4D radar has emerged as a promising next-generation sensor for improving the robustness of autonomous driving perception systems because of its stable sensing capability under adverse weather conditions. However, deploying 4D radar in embedded environments with limited hardware resources requires radar-representation preprocessing that jointly considers perception accuracy, real-time performance, and computational complexity. This paper proposes a preprocessing framework for 4D-radar-based 3D object detection. First, Percentile-based 3D Shape Preservation (P3DP) extracts point clouds from radar tensors while preserving object-shape information and suppressing noise and false alarms. Second, Multi-frame-based Noise Point Discrimination using Kernel Density Estimation (MF-KDE) improves the density and reliability of sparse radar point clouds. Finally, Embedded \& NetScore (ENS) evaluates suitability for embedded deployment by jointly considering accuracy, real-time performance, adverse-weather robustness, and model complexity.
发表机构
- Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
- Hyundai Motor Company（现代汽车公司）
机构由 AI 辅助整理，请以论文原文为准。
