arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04490eess.SPcs.AIeess.IV
收藏

RAVEN:用于高效脉冲波束成像的雷达自适应视觉编码器

RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation

Georgia Institute of Technology(佐治亚理工学院)

Anuvab Sen, Mir Sayeed Mohammad, Saibal Mukhopadhyay

AI总结:

RAVEN通过高效处理雷达数据实现目标检测和分割,采用自适应编码和早退出机制提升效率,减少计算量和延迟。

摘要:

本文提出RAVEN,一种计算高效的深度学习架构,用于FMCW雷达感知。该方法以脉冲方式流式处理原始ADC数据,通过独立接收器状态空间编码器保持MIMO结构,并使用可学习的跨天线混合模块恢复紧凑的虚拟阵列特征。它还引入了早退出机制,使模型在潜在状态稳定时仅使用部分脉冲做出决策。在汽车雷达基准测试中,该方法在目标检测和BEV自由空间分割方面表现优异,同时显著减少了计算量和端到端延迟,相比传统基于帧的雷达管道。

英文摘要:

This paper presents RAVEN, a computationally efficient deep learning architecture for FMCW radar perception. The method processes raw ADC data in a chirp-wise streaming manner, preserves MIMO structure through independent receiver state-space encoders, and uses a learnable cross-antenna mixing module to recover compact virtual-array features. It also introduces an early-exit mechanism so the model can make decisions using only a subset of chirps when the latent state has stabilized. Across automotive radar benchmarks, the approach reports strong object detection and BEV free-space segmentation performance while substantially reducing computation and end-to-end latency compared with conventional frame-based radar pipelines.

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。

↑