融合4D雷达运动信息与跨模态不确定性，提升激光雷达检测精度
ELMAR: Enhancing LiDAR Detection with 4D Radar Motion Awareness and Cross-modal Uncertainty
- 用动态运动感知模块捕捉4D雷达的物体运动信息
- 通过实例级边界框不确定性估计，减少模态错位，提升检测准确率
- 在VoD数据集上达74.89% mAP，实时推理速度30FPS，适合自动驾驶场景
激光雷达和4D雷达广泛应用于自动驾驶与机器人领域。激光雷达提供丰富的空间信息，4D雷达则具备速度测量能力且在恶劣条件下仍具鲁棒性。因此，越来越多研究聚焦于4D雷达与激光雷达的融合以增强感知能力。然而，不同模态间的错位常被忽视。为解决该问题并发挥两者优势，本文提出一种基于4D雷达运动状态与跨模态不确定性的激光雷达检测框架。首先，在特征提取阶段通过动态运动感知编码模块捕获4D雷达的物体运动信息，以增强其预测；随后，估计边界框的实例级不确定性，缓解跨模态错位，优化最终激光雷达检测结果。在View-of-Delft（VoD）数据集上的大量实验表明，本方法在全区域实现74.89%的mAP，驾驶走廊内达88.70%，同时保持30.02 FPS的实时推理速度。
原文摘要 · Abstract (English)
LiDAR and 4D radar are widely used in autonomous driving and robotics. While LiDAR provides rich spatial information, 4D radar offers velocity measurement and remains robust under adverse conditions. As a result, increasing studies have focused on the 4D radar-LiDAR fusion method to enhance the perception. However, the misalignment between different modalities is often overlooked. To address this challenge and leverage the strengths of both modalities, we propose a LiDAR detection framework enhanced by 4D radar motion status and cross-modal uncertainty. The object movement information from 4D radar is first captured using a Dynamic Motion-Aware Encoding module during feature extraction to enhance 4D radar predictions. Subsequently, the instance-wise uncertainties of bounding boxes are estimated to mitigate the cross-modal misalignment and refine the final LiDAR predictions. Extensive experiments on the View-of-Delft (VoD) dataset highlight the effectiveness of our method, achieving state-of-the-art performance with the mAP of 74.89% in the entire area and 88.70% within the driving corridor while maintaining a real-time inference speed of 30.02 FPS.
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。