光通信技术2024，Vol.48Issue(3)：52-56,5.DOI:10.13921/j.cnki.issn1002-5561.2024.03.007
基于扩散Transformer网络的激光雷达数据补全方法
Lidar data completion method based on diffusion Transformer network
摘要
Abstract
Due to factors such as equipment failure and environmental interference,lidar often encounters problems of missing data or noise interference during the data collection process,which seriously affect the subsequent analysis and application of the data.To solve this problem,the diffusion Transformer network(DT-Net)is introduced and used as a generator in combination with a Self-Attention unit discriminator.Additionally,a diffusion mechanism is designed for lidar data completion.The experi-mental results show that compared to the PoinTr method,the proposed approach achieves significant improvements in lidar data completion tasks,with an average Chamfer distance(CD)value reduced by approximately 1.79%and an F-Score value increased by approximately 1.88%.关键词
扩散机制/数据补全/激光雷达/实际应用Key words
diffusion mechanism/data completion/laser radar/practical application分类
信息技术与安全科学引用本文复制引用
李伟松,刘佳,张坤..基于扩散Transformer网络的激光雷达数据补全方法[J].光通信技术,2024,48(3):52-56,5.基金项目
河北省高等学校学科技术研究项目(No.ZD2020176)资助 （No.ZD2020176）
河北省技术创新引导计划项目(No.21470302D)资助. （No.21470302D）
