用雷达与摄像头融合生成更清晰的深度图，降低成本提升自动驾驶感知能力。
Toward a Low-Cost Perception System in Autonomous Vehicles: A Spectrum Learning Approach
- 基于巴特利特谱估计思想，将雷达和相机图像统一到空间谱子空间中
- 在复杂路况下使雷达深度图精度提升27.95%（UCD指标）
- 适合追求低成本高精度感知的自动驾驶系统部署
我们提出一种低成本新方法，通过融合深度神经网络4D雷达探测器获取的图像与传统相机RGB图像，生成更稠密的自动驾驶深度图。该方法引入受巴特利特空间谱估计启发的新型像素位置编码算法，将雷达深度图与RGB图像映射至统一的像素图像子空间——空间谱，从而有效学习二者间的相似性与差异性。本方法充分利用高分辨率相机图像训练雷达深度图生成模型，克服了传统雷达探测器在复杂交通环境中的局限性，显著提升了雷达输出清晰度。我们设计了专用于雷达深度图与RGB图像的谱估计算法、端到端数据驱动生成模型训练框架，以及面向自动驾驶车辆运行的相机-雷达部署方案。实验结果表明，该方法在单向切比雪夫距离（UCD）上优于当前最优水平27.95%。
原文摘要 · Abstract (English)
We present a cost-effective new approach for generating denser depth maps for Autonomous Driving (AD) and Autonomous Vehicles (AVs) by integrating the images obtained from deep neural network (DNN) 4D radar detectors with conventional camera RGB images. Our approach introduces a novel pixel positional encoding algorithm inspired by Bartlett's spatial spectrum estimation technique. This algorithm transforms both radar depth maps and RGB images into a unified pixel image subspace called the Spatial Spectrum, facilitating effective learning based on their similarities and differences. Our method effectively leverages high-resolution camera images to train radar depth map generative models, addressing the limitations of conventional radar detectors in complex vehicular environments, thus sharpening the radar output. We develop spectrum estimation algorithms tailored for radar depth maps and RGB images, a comprehensive training framework for data-driven generative models, and a camera-radar deployment scheme for AV operation. Our results demonstrate that our approach also outperforms the state-of-the-art (SOTA) by 27.95% in terms of Unidirectional Chamfer Distance (UCD).
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。