Separated RoadTopoFormer

TL;DR

The paper introduces Separated RoadTopoFormer, an end-to-end framework for autonomous driving scene understanding that detects lanes and traffic elements while reasoning their relationships, improving upon previous methods that neglect these connections.

Contribution

It proposes a novel end-to-end model that separately optimizes detection and relationship reasoning modules for better scene understanding in autonomous driving.

Findings

Achieved 0.445 OLS score, competitive with state-of-the-art.

Effectively detects lanes and traffic elements with relationship reasoning.

Modules are optimized separately and integrated with minimal fine-tuning.

Abstract

Understanding driving scenarios is crucial to realizing autonomous driving. Previous works such as map learning and BEV lane detection neglect the connection relationship between lane instances, and traffic elements detection tasks usually neglect the relationship with lane lines. To address these issues, the task is presented which includes 4 sub-tasks, the detection of traffic elements, the detection of lane centerlines, reasoning connection relationships among lanes, and reasoning assignment relationships between lanes and traffic elements. We present Separated RoadTopoFormer to tackle the issues, which is an end-to-end framework that detects lane centerline and traffic elements with reasoning relationships among them. We optimize each module separately to prevent interaction with each other and aggregate them together with few finetunes. For two detection heads, we adopted a DETR-like architecture to detect objects, and for the relationship head, we concat two instance features from front detectors and feed them to the classifier to obtain relationship probability. Our final submission achieves 0.445 OLS, which is competitive in both sub-task and combined scores.