Timealign: A multi-modal object detection method for time misalignment fusing in autonomous driving

TL;DR

This paper introduces Timealign, a novel method for addressing time misalignment in multi-modal autonomous driving perception by using historical LiDAR data to improve real-time object detection accuracy.

Contribution

The paper proposes a Timealign module that predicts and fuses LiDAR features with current observations to mitigate time lag issues, enhancing multi-modal perception robustness.

Findings

Improved object detection accuracy under time lag conditions

Effective fusion of historical and current LiDAR data

Enhanced robustness of multi-modal perception systems

Abstract

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.