Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models

TL;DR

This paper introduces a novel lane graph extraction method from aerial imagery that refines CNN-generated lane masks using diffusion models, significantly improving graph connectivity and quality for autonomous driving applications.

Contribution

The paper presents a new approach combining CNNs and diffusion models for lane mask refinement, outperforming existing methods in lane graph extraction accuracy.

Findings

Improved GEO F1 and TOPO F1 scores by 1.5% and 3.5% over CNN-based methods.

Achieved 28% and 34% improvements in GEO F1 and TOPO F1 over prior diffusion approaches.

Ablation studies confirm the effectiveness of the proposed refinement components.

Abstract

The lane graph is critical for applications such as autonomous driving and lane-level route planning. While previous research has focused on extracting lane-level graphs from aerial imagery using convolutional neural networks (CNNs) followed by post-processing segmentation-to-graph algorithms, these methods often face challenges in producing sharp and complete segmentation masks. Challenges such as occlusions, variations in lighting, and changes in road texture can lead to incomplete and inaccurate lane masks, resulting in poor-quality lane graphs. To address these challenges, we propose a novel approach that refines the lane masks, output by a CNN, using diffusion models. Experimental results on a publicly available dataset demonstrate that our method outperforms existing methods based solely on CNNs or diffusion models, particularly in terms of graph connectivity. Our lane mask refinement approach enhances the quality of the extracted lane graph, yielding gains of approximately 1.5\% in GEO F1 and 3.5\% in TOPO F1 scores over the best-performing CNN-based method, and improvements of 28\% and 34\%, respectively, compared to a prior diffusion-based approach. Both GEO F1 and TOPO F1 scores are critical metrics for evaluating lane graph quality. Additionally, ablation studies are conducted to evaluate the individual components of our approach, providing insights into their respective contributions and effectiveness.