The 1st-place Solution for CVPR 2023 OpenLane Topology in Autonomous Driving Challenge
This work addresses the challenge of accurate lane topology prediction in autonomous driving, but it is incremental as it builds on existing detection methods.
The paper tackled the problem of topology reasoning for autonomous driving by developing a multi-stage framework that combines centerline detection with PETRv2 and traffic element detection with YOLOv8, achieving 55% OLS on the OpenLaneV2 test set and surpassing the second-place solution by 8 points.
We present the 1st-place solution of OpenLane Topology in Autonomous Driving Challenge. Considering that topology reasoning is based on centerline detection and traffic element detection, we develop a multi-stage framework for high performance. Specifically, the centerline is detected by the powerful PETRv2 detector and the popular YOLOv8 is employed to detect the traffic elements. Further, we design a simple yet effective MLP-based head for topology prediction. Our method achieves 55\% OLS on the OpenLaneV2 test set, surpassing the 2nd solution by 8 points.