BEVFastLine: Single Shot Fast BEV Line Detection for Automated Parking Applications

Praveen Narasappareddygari, Venkatesh Karunamoorthy, Shubham Sonarghare, Ganesh Sistu, Prasad Deshpande

2024

Abstract

In autonomous parking scenarios, accurate near-field environmental perception is crucial for smooth operations. Parking line detection, unlike the well-understood lane detection, poses unique challenges due to its lack of spatial consistency in orientation, location, and varied appearances in color, pattern, and background surfaces. Consequently, state-of-the-art models for lane detection, which rely on anchors and offsets, are not directly applicable. This paper introduces BEVFastLine, a novel end-to-end line marking detection architecture in Birds Eye View (BEV) space, designed for 360 ◦ multi-camera perception applications. BEVFastLine integrates our single-shot line detection methodology with advanced Inverse Perspective Mapping (IPM) techniques, notably our fast splatting technique, to efficiently detect line markings in varied spatial contexts. This approach is suitable for real-time hardware in Level-3 automated vehicles. BEVFastLine accurately localizes parking lines in BEV space with up to 10 cm precision. Our methods, including the 4X faster Fast Splat and single-shot detection, surpass LSS and OFT in accuracy, achieving 80.1% precision, 90% recall, and nearly doubling the performance of BEV-based segmentation and polyline models. This streamlined solution is highly effective in complex, dynamic parking environments, offering high precision localization within 10 meters around the ego vehicle.

Paper Citation

in Harvard Style

Narasappareddygari P., Karunamoorthy V., Sonarghare S., Sistu G. and Deshpande P. (2024). BEVFastLine: Single Shot Fast BEV Line Detection for Automated Parking Applications. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 220-231. DOI: 10.5220/0012435700003660

in Bibtex Style

@conference{visapp24,
author={Praveen Narasappareddygari and Venkatesh Karunamoorthy and Shubham Sonarghare and Ganesh Sistu and Prasad Deshpande},
title={BEVFastLine: Single Shot Fast BEV Line Detection for Automated Parking Applications},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={220-231},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012435700003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - BEVFastLine: Single Shot Fast BEV Line Detection for Automated Parking Applications
SN - 978-989-758-679-8
AU - Narasappareddygari P.
AU - Karunamoorthy V.
AU - Sonarghare S.
AU - Sistu G.
AU - Deshpande P.
PY - 2024
SP - 220
EP - 231
DO - 10.5220/0012435700003660
PB - SciTePress