arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04723eess.SPeess.IV
收藏

使用 RaDelft 数据集的深度汽车雷达检测器

A Deep Automotive Radar Detector using the RaDelft Dataset

Ignacio Roldan, Andras Palffy, Julian F. P. Kooij, Dariu M. Gavrila, Francesco Fioranelli, Alexander Yarovoy

AI总结:

本文提出一种数据驱动的汽车雷达检测方法,利用无标签激光雷达数据作为真值训练神经网络,仅输入雷达数据即可生成保留目标形状大小的类激光雷达点云,在 Chamfer 距离指标上显著优于传统 CFAR 和现有深度学习方法。

摘要:

本文考虑了使用高分辨率汽车雷达在复杂环境中检测多个扩展目标的问题。提出了一种数据驱动的方法,使用无标签的同步激光雷达数据作为真值,训练一个仅以雷达数据为输入的神经网络。为此,使用演示车辆在 Delft 市的不同地点记录了新颖的、大规模的、真实的和多传感器的 RaDelft 数据集。该数据集以及文档和示例代码已公开提供给汽车雷达或机器感知领域的研究人员。所提出的数据驱动检测器能够仅使用高分辨率系统的雷达数据生成类似激光雷达的点云,从而保留扩展目标的形状和大小。结果与传统的 CFAR 检测器以及该方法的变体进行了比较,以模拟文献中的现有方法,使用检测概率、虚警概率和 Chamfer 距离作为性能指标。此外,还进行了消融研究,以评估多普勒和时间信息对检测性能的影响。所提出的方法在 Chamfer 距离方面优于不同的基线,与传统的 CFAR 检测器相比减少了 75%,与改进的最先进的基于深度学习的方法相比减少了 10%。

英文摘要:

The detection of multiple extended targets in complex environments using high-resolution automotive radar is considered. A data-driven approach is proposed where unlabeled synchronized lidar data is used as ground truth to train a neural network with only radar data as input. To this end, the novel, large-scale, real-life, and multi-sensor RaDelft dataset has been recorded using a demonstrator vehicle in different locations in the city of Delft. The dataset, as well as the documentation and example code, is publicly available for those researchers in the field of automotive radar or machine perception. The proposed data-driven detector is able to generate lidar-like point clouds using only radar data from a high-resolution system, which preserves the shape and size of extended targets. The results are compared against conventional CFAR detectors as well as variations of the method to emulate the available approaches in the literature, using the probability of detection, the probability of false alarm, and the Chamfer distance as performance metrics. Moreover, an ablation study was carried out to assess the impact of Doppler and temporal information on detection performance. The proposed method outperforms the different baselines in terms of Chamfer distance, achieving a reduction of 75% against conventional CFAR detectors and 10% against the modified state-of-the-art deep learning-based approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑