Learning to Generate Vectorized Maps at Intersections with Multiple Roadside Cameras

Vectorized maps are indispensable for precise navigation and the safe operation of autonomous vehicles. Traditional methods for constructing these maps fall into two categories: offline techniques, which rely on expensive, labor-intensive LiDAR data collection and manual annotation, and online approaches that use onboard cameras to reduce costs but suffer from limited performance, especially at complex intersections. To bridge this gap, we introduce the Multiple Roadside Camera-based Vectorized Map approach, MRC-VMap, a cost-effective, vision-centric, end-to-end neural network designed to generate high-definition vectorized maps directly at intersections. Leveraging existing roadside surveillance cameras, MRC-VMap directly converts time-aligned, multi-directional images into vectorized map representations. This integrated solution lowers the need for additional intermediate modules-such as separate feature extraction and Bird’s-Eye View (BEV) conversion steps-thus reducing both computational overhead and error propagation. Moreover, the use of multiple camera views enhances mapping completeness, mitigates occlusions, and provides robust performance under practical deployment constraints. Extensive experiments conducted on 4, 000 intersections across 4 major metropolitan areas in China demonstrate that MRC-VMap not only outperforms state-of-the-art online methods but also achieves accuracy comparable to high-cost LiDAR-based approaches, thereby offering a scalable and efficient solution for modern autonomous navigation systems.

Authors

• Quanxin Zheng
• Miao Fan
• Shengtong Xu
• Linghe Kong
• Haoyi Xiong

Keywords

• Costs
• Surveillance
• Scalability
• Urban areas
• Neural networks
• Robot vision systems
• Cameras
• Vectors
• Real-time systems
• Autonomous vehicles
• Multiple Cameras
• Vector Map
• Roadside Camera
• Neural Network
• Scalable
• Error Propagation
• Manual Annotation
• Bird’s Eye
• Vehicle Operation
• Lidar Data
• Complex Intersections
• Major Metropolitan Areas
• High Cost
• Image Features
• Major Cities
• Classification Loss
• Mesh Generation
• Image Feature Extraction
• Feature Pyramid Network
• Geometric Transformation
• Map Elements
• Conventional Convolutional Neural Networks
• Road Boundary
• Matching Cost
• Camera Data
• Permutation Group
• Feature Fusion Network
• Real-time Mapping
• LiDAR Point Clouds
• vectorized maps
• roadside cameras
• generative neural networks
• edge computing