Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance

Roadside bird’s eye view (BEV) perception can enhance the comprehensive environmental awareness required for autonomous driving systems. Current approaches typically concentrate on BEV perception from the perspective of the vehicle, requiring precise camera calibration or depth estimation, leading t...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Zhang, Yilin Gao, Zhiyuan Jiang, Ruiqing Mao, Sheng Zhou
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/3919
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115566960902144
author Wei Zhang
Yilin Gao
Zhiyuan Jiang
Ruiqing Mao
Sheng Zhou
author_facet Wei Zhang
Yilin Gao
Zhiyuan Jiang
Ruiqing Mao
Sheng Zhou
author_sort Wei Zhang
collection DOAJ
description Roadside bird’s eye view (BEV) perception can enhance the comprehensive environmental awareness required for autonomous driving systems. Current approaches typically concentrate on BEV perception from the perspective of the vehicle, requiring precise camera calibration or depth estimation, leading to potential inaccuracies. We introduce a calibration-free roadside BEV perception architecture, which utilizes elevated roadside cameras in conjunction with the vehicle position transmitted via cellular vehicle-to-everything (C-V2X) independently of camera calibration parameters. To enhance robustness against practical issues such as V2X communication delay, packet loss, and positioning noise, we simulate real-world uncertainties by injecting random noise into the coordinate input and varying the proportion of vehicles providing location data. Experiments on the DAIR-V2X dataset demonstrate that the architecture achieves superior performance compared to calibration-based and calibration-free baselines, highlighting its effectiveness in roadside BEV perception.
format Article
id doaj-art-9c299668529141e2bcb3b6797bea75cd
institution OA Journals
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-9c299668529141e2bcb3b6797bea75cd2025-08-20T02:36:31ZengMDPI AGSensors1424-82202025-06-012513391910.3390/s25133919Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position AssistanceWei Zhang0Yilin Gao1Zhiyuan Jiang2Ruiqing Mao3Sheng Zhou4Information and Communication Engineering, Shanghai University, Shanghai 200444, ChinaInformation and Communication Engineering, Shanghai University, Shanghai 200444, ChinaInformation and Communication Engineering, Shanghai University, Shanghai 200444, ChinaElectronic Engineering, Tsinghua University, Beijing 100190, ChinaElectronic Engineering, Tsinghua University, Beijing 100190, ChinaRoadside bird’s eye view (BEV) perception can enhance the comprehensive environmental awareness required for autonomous driving systems. Current approaches typically concentrate on BEV perception from the perspective of the vehicle, requiring precise camera calibration or depth estimation, leading to potential inaccuracies. We introduce a calibration-free roadside BEV perception architecture, which utilizes elevated roadside cameras in conjunction with the vehicle position transmitted via cellular vehicle-to-everything (C-V2X) independently of camera calibration parameters. To enhance robustness against practical issues such as V2X communication delay, packet loss, and positioning noise, we simulate real-world uncertainties by injecting random noise into the coordinate input and varying the proportion of vehicles providing location data. Experiments on the DAIR-V2X dataset demonstrate that the architecture achieves superior performance compared to calibration-based and calibration-free baselines, highlighting its effectiveness in roadside BEV perception.https://www.mdpi.com/1424-8220/25/13/3919cellular-V2X (C-V2X)roadside bird’s eye view (BEV) perceptioncalibration-free perception
spellingShingle Wei Zhang
Yilin Gao
Zhiyuan Jiang
Ruiqing Mao
Sheng Zhou
Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
Sensors
cellular-V2X (C-V2X)
roadside bird’s eye view (BEV) perception
calibration-free perception
title Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
title_full Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
title_fullStr Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
title_full_unstemmed Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
title_short Calibration-Free Roadside BEV Perception with V2X-Enabled Vehicle Position Assistance
title_sort calibration free roadside bev perception with v2x enabled vehicle position assistance
topic cellular-V2X (C-V2X)
roadside bird’s eye view (BEV) perception
calibration-free perception
url https://www.mdpi.com/1424-8220/25/13/3919
work_keys_str_mv AT weizhang calibrationfreeroadsidebevperceptionwithv2xenabledvehiclepositionassistance
AT yilingao calibrationfreeroadsidebevperceptionwithv2xenabledvehiclepositionassistance
AT zhiyuanjiang calibrationfreeroadsidebevperceptionwithv2xenabledvehiclepositionassistance
AT ruiqingmao calibrationfreeroadsidebevperceptionwithv2xenabledvehiclepositionassistance
AT shengzhou calibrationfreeroadsidebevperceptionwithv2xenabledvehiclepositionassistance