VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
This work addresses the need for scalable and efficient HD map creation for autonomous driving systems, representing an incremental improvement in annotation methods.
The authors tackled the problem of efficiently generating high-definition (HD) maps for autonomous driving by developing a vectorized map annotation system (VMA) that uses a divide-and-conquer scheme and unified point sequence representation, resulting in an average annotation time of 160 minutes per scene and a 52.3% reduction in human cost.
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for efficiently generating HD map of large-scale driving scene. We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene. VMA is highly efficient and extensible, requiring negligible human effort, and flexible in terms of spatial scale and element type. We quantitatively and qualitatively validate the annotation performance on real-world urban and highway scenes, as well as NYC Planimetric Database. VMA can significantly improve map generation efficiency and require little human effort. On average VMA takes 160min for annotating a scene with a range of hundreds of meters, and reduces 52.3% of the human cost, showing great application value. Code: https://github.com/hustvl/VMA.