解决自动驾驶中传感器时间不同步问题，提升多模态感知精度
Timealign: A multi-modal object detection method for time misalignment fusing in autonomous driving
- 基于历史帧的LiDAR特征预测与融合，缓解数据延迟带来的时序错位
- 在GraphBEV框架上实现端到端对齐，显著提升时序不一致下的检测性能
- 适用于真实场景中存在数据传输延迟的自动驾驶系统
多模态感知方法在自动驾驶领域蓬勃发展，因其能有效利用不同传感器的互补信息。这类方法依赖于传感器间的标定与同步以获取准确环境信息。尽管已有研究关注空间对齐鲁棒性，针对时间对齐的研究仍较少。现实中LiDAR点云存在实时传输挑战，本文利用历史帧的LiDAR特征，在存在延迟时更好地对齐特征。设计了Timealign模块，基于当前观测预测并融合历史帧特征，用于应对时间不同步问题，集成于SOTA GraphBEV框架中。
原文摘要 · Abstract (English)
The multi-modal perception methods are thriving in the autonomous driving field due to their better usage of complementary data from different sensors. Such methods depend on calibration and synchronization between sensors to get accurate environmental information. There have already been studies about space-alignment robustness in autonomous driving object detection process, however, the research for time-alignment is relatively few. As in reality experiments, LiDAR point clouds are more challenging for real-time data transfer, our study used historical frames of LiDAR to better align features when the LiDAR data lags exist. We designed a Timealign module to predict and combine LiDAR features with observation to tackle such time misalignment based on SOTA GraphBEV framework.
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。