Maptrv2: An end-to-end framework for online vectorized hd map construction
High-definition (HD) map provides abundant and precise static environmental information of
the driving scene, serving as a fundamental and indispensable component for planning in …
the driving scene, serving as a fundamental and indispensable component for planning in …
Data-centric evolution in autonomous driving: A comprehensive survey of big data system, data mining, and closed-loop technologies
The aspiration of the next generation's autonomous driving (AD) technology relies on the
dedicated integration and interaction among intelligent perception, prediction, planning, and …
dedicated integration and interaction among intelligent perception, prediction, planning, and …
High-definition maps construction based on visual sensor: A comprehensive survey
In recent years, the field of autonomous vehicles has seen a significant increase in
academic research, with high-definition (HD) maps emerging as a critical component of …
academic research, with high-definition (HD) maps emerging as a critical component of …
A vision-centric approach for static map element annotation
J Zhang, S Chen, H Yin, R Mei, X Liu… - … on Robotics and …, 2024 - ieeexplore.ieee.org
The recent development of online static map element (aka HD Map) construction algorithms
has raised a vast demand for data with ground truth annotations. However, available public …
has raised a vast demand for data with ground truth annotations. However, available public …
LaneDAG: Automatic HD Map Topology Generator Based on Geometry and Attention Fusion Mechanism
In high-definition maps (HD maps), the road lane centerline and lane topology graph play
essential roles in navigation, planning, and decision-making. Existing research focusing on …
essential roles in navigation, planning, and decision-making. Existing research focusing on …
IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction
Online vector map construction based on visual data can bypass the processes of data
collection, post-processing, and manual annotation required by traditional map construction …
collection, post-processing, and manual annotation required by traditional map construction …
PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation
H Ishikawa, T Iida, Y Konishi, Y Aoki - arXiv preprint arXiv:2403.12530, 2024 - arxiv.org
Generating annotations for bird's-eye-view (BEV) segmentation presents significant
challenges due to the scenes' complexity and the high manual annotation cost. In this work …
challenges due to the scenes' complexity and the high manual annotation cost. In this work …
CAMAv2: A Vision-Centric Approach for Static Map Element Annotation
S Chen, J Zhang, R Mei, Y Cai, H Yin, T Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
The recent development of online static map element (aka HD map) construction algorithms
has raised a vast demand for data with ground truth annotations. However, available public …
has raised a vast demand for data with ground truth annotations. However, available public …
TopoSense: agent driven topological graph extraction from remote sensing image
M Zhang, B Yang, J Gong, X Hu - ISPRS Annals of the …, 2024 - isprs-annals.copernicus.org
Automatic topological graph extraction is critical for intelligent remote sensing image
interpretation and cartographic representation. However, existing approaches neither adopt …
interpretation and cartographic representation. However, existing approaches neither adopt …
[PDF][PDF] Technical Report for Online HD Map Construction in CVPR 2023 Autonomous Driving Challenge
W Luo, Z Liu, H Luo, J Zhao, N Xu, H Technology - opendrivelab.com
This technical report presents the third winning model for Online HD Map Construction, a
task newly introduced in CVPR 2023 Autonomous Driving Challenge. Compared to …
task newly introduced in CVPR 2023 Autonomous Driving Challenge. Compared to …