为自动驾驶相机雷达数据集生成真实噪声，提升检测系统鲁棒性。
Synthesizing and Identifying Noise Levels in Autonomous Vehicle Camera Radar Datasets
- 构建合成噪声数据增强流程，模拟真实干扰下的传感器故障。
- 轻量级噪声识别网络在10086张图像和2145个点云上达到54.4%准确率。
- 适用于提升自动驾驶系统在恶劣环境下的感知可靠性。
物体检测与跟踪是自动驾驶导航的核心环节。近年来，基于神经网络的检测方法在多个数据集上取得显著进展。然而，多数研究聚焦于性能指标，较少关注检测与跟踪流程对传感器故障的鲁棒性。本文提出一种面向相机-雷达自动驾驶数据集的合成数据增强流程，旨在真实模拟传感器故障及现实干扰导致的数据退化。我们还训练并测试了一个基线轻量级噪声识别神经网络，在包含10086张图像和2145个雷达点云的数据集上，对11类噪声实现了54.4%的整体识别准确率。
原文摘要 · Abstract (English)
Detecting and tracking objects is a crucial component of any autonomous navigation method. For the past decades, object detection has yielded promising results using neural networks on various datasets. While many methods focus on performance metrics, few projects focus on improving the robustness of these detection and tracking pipelines, notably to sensor failures. In this paper we attempt to address this issue by creating a realistic synthetic data augmentation pipeline for camera-radar Autonomous Vehicle (AV) datasets. Our goal is to accurately simulate sensor failures and data deterioration due to real-world interferences. We also present our results of a baseline lightweight Noise Recognition neural network trained and tested on our augmented dataset, reaching an overall recognition accuracy of 54.4\% on 11 categories across 10086 images and 2145 radar point-clouds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。