北京交通大学学报2025，Vol.49Issue(3)：137-146,10.DOI:10.11860/j.issn.1673-0291.20240077
基于交叉注意力的车载环视系统外参标定算法
Extrinsic calibration algorithm for surround-view systems based on cross-attention
摘要
Abstract
To address the challenge of extrinsic parameter calibration for multi-camera automotive surround-view systems,this paper proposes an extrinsic parameter calibration algorithm based on a cross-attention mechanism.First,multi-scale features from multi-view images are independently extracted using residual convolutional modules to capture fine-grained image details.Then,a cross-attention module is introduced to learn global features of each camera image as well as the inter-camera feature relationships with surrounding cameras,thereby enhancing the overall feature representation capability.These features are subsequently integrated via a feature fusion module,which combines outputs from both the residual convolutional and cross-attention modules to regress the extrinsic parameters.Finally,the proposed model is validated on two datasets through perfor-mance evaluation and ablation studies.Experimental results demonstrate that,compared with existing extrinsic parameter calibration algorithms based on lane lines and textures,the algorithm proposed in this paper has better generalization and robustness in different environments,with significant improve-ments in performance metrics and bird's-eye view stitching visualization results.Compared with exist-ing extrinsic parameter calibration algorithms based on lane markings and texture cues,the proposed algorithm exhibits superior generalization and robustness across diverse environments,with notable improvements in quantitative performance metrics and bird's-eye view stitching quality.Specifically,the algorithm achieves absolute reprojection and photometric errors of 3.1 and 16.7,respectively,representing improvements of 8.82％and 8.74％over the current state-of-the-art weakly-supervised extrinsic self-calibration network(WESNet).The research findings provide technical support for online extrinsic parameter calibration in automotive surround-view systems.关键词
环视系统/深度学习/交叉注意力机制/外参标定Key words
surround-view system/deep learning/cross-attention/extrinsic calibration分类
信息技术与安全科学引用本文复制引用
黄书隽,林春雨,覃雷栋,金智勇,赵耀..基于交叉注意力的车载环视系统外参标定算法[J].北京交通大学学报,2025,49(3):137-146,10.基金项目
国家自然科学基金(62172032) （62172032）
中央高校基本科研业务费专项资金(2023JBZY032)National Natural Science Foundation of China(62172032) （2023JBZY032）
Fundamental Research Funds for the Central Universities(2023JBZY032) （2023JBZY032）
