Correlation-based approach to online map validation

Workshop on Online Map Validation, IEEE Intelligent Vehicles Symposium (IV), 2020

autonomous-driving
map-validation
A model-based method for HD map validation using spatial and temporal correlation of smart sensors, fusing independent regional assessments to identify map areas inconsistent with live sensor data.
Authors

Andrea Fabris

Luca Parolini

Sebastian Schneider

Angelo Cenedese

Published year

2020

Authors
Andrea Fabris, Luca Parolini, Sebastian Schneider, Angelo Cenedese
Published
IEEE Xplore
Preprint
PDF
DOI
DOI

Spatial and temporal correlation approach for map validation

Abstract

This paper presents a method for validating HD maps through spatial and temporal correlation of smart sensors that analyze map regions independently. Results are fused across locations and time to identify map areas consistent with sensor data. The approach is model-based and does not require deep learning, providing a lightweight complementary method to similarity-learning techniques.

Related

Citation

BibTeX citation:
@inproceedings{fabris2020,
  author = {Fabris, Andrea and Parolini, Luca and Schneider, Sebastian
    and Cenedese, Angelo},
  title = {Correlation-Based Approach to Online Map Validation},
  booktitle = {First Workshop on Online Map Validation and Road Model
    Creation, IEEE Intelligent Vehicles Symposium (IV)},
  date = {2020-10-01},
  url = {https://lucaparolini.com/publications/papers/correlation-map-validation-2020/},
  doi = {10.1109/iv47402.2020.9304837},
  langid = {en}
}
For attribution, please cite this work as:
A. Fabris, L. Parolini, S. Schneider, and A. Cenedese, “Correlation-based approach to online map validation,” in First Workshop on Online Map Validation and Road Model Creation, IEEE Intelligent Vehicles Symposium (IV), Oct. 2020. doi: 10.1109/iv47402.2020.9304837.