CalibRBEV: Multi-Camera Calibration via Reversed Bird's-eye-view Representations for Autonomous Driving
Lists
Only you see this
Abstract
Camera calibration consists of determining the intrinsic and extrinsic parameters of an imaging system, which forms the fundamental basis for various computer vision tasks and applications, e.g., robotics and autonomous driving (AD). However, prevailing camera calibration models pose a time-consuming and labor-intensive off-board process particularly in mass production settings, while simultaneously lacking exploration of real-world autonomous driving scenarios. To this end, in this paper, inspired by recent advancements in bird's-eye-view (BEV) perception models, we proposes a novel automatic multi-camera Calibration method via Reversed BEV representations for autonomous driving, termed CalibRBEV. Specifically, the proposed CalibRBEV model primarily comprises two stages. Initially, we innovatively reverse the BEV perception pipeline, reconstructing bounding boxes through an attention auto-encoder module to fully extract the latent reversed BEV representations. Subsequently, the obtained representations from encoder are interacted with the surrounding multi-view image features for further refinement and calibration parameters prediction. Extensive experimental results on nuScenes and Waymo datasets validate the effectiveness of our proposed model.
BibTeX
@inproceedings{liao2024calibrbev,
author = {Wenlong Liao and Sunyuan Qiang and Xianfei Li and Xiaolei Chen and Haoyu Wang and Yanyan Liang and Junchi Yan and Tao He and Pai Peng},
title = {{CalibRBEV: Multi-Camera Calibration via Reversed Bird's-eye-view Representations for Autonomous Driving}},
booktitle = {ACM Multimedia},
year = {2024},
doi = {10.1145/3664647.3680572},
}Loading related content...