Verification and validation procedure for high-definition maps in Taiwan

Chiang, Kai-Wei; Wang, Chi-Kuei; Hong, Jung-Hong; Li, Peiling; Yang, Chin-Sung; Tsai, Meng-Lun; Lee, Jeffrey; Lin, Sean

doi:10.1007/s44212-022-00014-0

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High Definition (HD) maps are required to exploit the full functionality of autonomous driving (Seif and Hu, 2016;Chiang et al, 2022). To create such maps, modeling of roads and their surroundings is needed; besides, such accurate, continuously updated road databases can effectively support numerous applications, e.g., road design, urban planning, traffic management, road monitoring, and vehicle simulations.…”

Section: Introduction Introduction Introduction Introductionmentioning

confidence: 99%

Comparative analysis of Road Scanning Techniques

et al. 2023

View full text Add to dashboard Cite

A three-dimensional road point cloud is not only useful for civil engineers (road rehabilitation, road condition assessment) but can also be useful for vehicle engineers (autonomous vehicle driving scenario, vehicle dynamics simulation). Currently, there are several scanning techniques can be used to obtain these point clouds, such as terrestrial laser scanning (TLS), mobile laser scanning (MLS), airborne laser scanning (ALS), unmanned aerial vehicle (UAV) photogrammetry or UAV laser scanning. This paper discusses the investigation of four road surface scanning techniques by comparing their point clouds and the derived products. The comparison was performed for a section of a road with 1136 m length and 4 m width, the TLS survey provided the reference data. Aspects of point cloud evaluation included geometric accuracy, density, and the parameters of plane-fitting. CRG models were created from all studied point clouds to compare the difference between the final products to be used by the automotive industry. The results show that the MLS and the UAV photogrammetry generated the most accurate point cloud, while UAV laser scanning accuracy was the lowest. Similarly, the CRG models comparison showed that there was no significant difference between MLS and TLS models, and the UAV photogrammetry gave a smoother variation relative to the reference surface. Whereas the largest differences were noted for the CRG model derived from the UAV laser scanning models.

show abstract

Section: Introduction Introduction Introduction Introductionmentioning

confidence: 99%

Comparative analysis of Road Scanning Techniques

et al. 2023

View full text Add to dashboard Cite

show abstract

L2T-BEV: Local Lane Topology Prediction from Onboard Surround-View Cameras in Bird’s Eye View Perspective

Ye,

Li,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Anomaly Detection and Quality Indicators for Digital Maps Used in ADAS Applications

Veber,

Bai N,

Bhat

et al. 2024

SAE Technical Paper Series

View full text Add to dashboard Cite

<div class="section abstract"><div class="htmlview paragraph">With the evolution of Advanced Driver Assistance Systems (ADAS), the gap towards Autonomous Driving (AD) is continuously narrowing. This progress is made possible using digital maps as one of the critical sources along with other ADAS sensors. Correct map data is crucial for the proper functioning of ADAS functions. This demands the need to evaluate the correctness of the map data regularly and efficiently. This work proposes a framework to quantify the map data correctness systematically. The framework algorithmically detects error locations in a map database and then derives KPIs from these error locations. The framework helps to identify issues in the map data related to the internal data consistency or heuristic rules. The framework consists of process automation in Python and map database checks in SQL. The proposed framework defines validation methodology that achieves goals like: (1) KPIs for map data reliability (2) systematic error identification. The framework was evaluated with maps from various sources. The framework yields results quickly and efficiently so that it can be regularly executed well before vehicle testing. In addition, the efficient KPI calculation permits the control of relevant map properties over subsequent map releases.</div></div>

show abstract

Verification and validation procedure for high-definition maps in Taiwan

Cited by 3 publications

References 4 publications

Comparative analysis of Road Scanning Techniques

Comparative analysis of Road Scanning Techniques

L2T-BEV: Local Lane Topology Prediction from Onboard Surround-View Cameras in Bird’s Eye View Perspective

Anomaly Detection and Quality Indicators for Digital Maps Used in ADAS Applications

Contact Info

Product

Resources

About