Road Mapping and Localization using Sparse Semantic Visual Features
This addresses the problem of accurate and efficient navigation for autonomous vehicles, representing an incremental improvement over existing feature-based approaches.
The paper tackles visual mapping and localization for autonomous vehicles by using semantic road elements like lights, signs, and lanes, resulting in improved pose accuracy and map compactness compared to traditional methods.
We present a novel method for visual mapping and localization for autonomous vehicles, by extracting, modeling, and optimizing semantic road elements. Specifically, our method integrates cascaded deep models to detect standardized road elements instead of traditional point features, to seek for improved pose accuracy and map representation compactness. To utilize the structural features, we model road lights and signs by their representative deep keypoints for skeleton and boundary, and parameterize lanes via piecewise cubic splines. Based on the road semantic features, we build a complete pipeline for mapping and localization, which includes a) image processing front-end, b) sensor fusion strategies, and c) optimization backend. Experiments on public datasets and our testing platform have demonstrated the effectiveness and advantages of our method by outperforming traditional approaches.