Multi-Dimensional Spatial-Temporal Fusion for Pedestrian Trajectory Prediction

Tong Luo, Huiliang Shang, Zengwen Li, Changxue Chen
{"title":"Multi-Dimensional Spatial-Temporal Fusion for Pedestrian Trajectory Prediction","authors":"Tong Luo, Huiliang Shang, Zengwen Li, Changxue Chen","doi":"10.1109/INSAI56792.2022.00040","DOIUrl":null,"url":null,"abstract":"Pedestrian trajectory prediction is a key technology in autonomous driving. Due to the variability of pedestrian trajectories and complex interactions, effective spatial-temporal feature extraction and fusion of trajectories is a key point. Most previous studies did not explicitly consider the trend of the interaction between pedestrians, which can help the model focus on adjacent pedestrians with high impact on the future motion of the predicted target. To address this issue, we propose a Multi-dimensional Spatial-Temporal fusion Graph attention network, called MST-G. Specifically, the directed graphs is used to model the interactions among pedestrians. Meanwhile, on the basis of using spatial-temporal convolution to obtain trajectory features with interaction, we add edge convolution to extract the temporal continuity of the interaction. Finally, the LSTM codec is used for trajectory generation. Experiments show that our model achieves better performance on two publicly available population datasets (ETH and UCY).","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 2nd International Conference on Networking Systems of AI (INSAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INSAI56792.2022.00040","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Pedestrian trajectory prediction is a key technology in autonomous driving. Due to the variability of pedestrian trajectories and complex interactions, effective spatial-temporal feature extraction and fusion of trajectories is a key point. Most previous studies did not explicitly consider the trend of the interaction between pedestrians, which can help the model focus on adjacent pedestrians with high impact on the future motion of the predicted target. To address this issue, we propose a Multi-dimensional Spatial-Temporal fusion Graph attention network, called MST-G. Specifically, the directed graphs is used to model the interactions among pedestrians. Meanwhile, on the basis of using spatial-temporal convolution to obtain trajectory features with interaction, we add edge convolution to extract the temporal continuity of the interaction. Finally, the LSTM codec is used for trajectory generation. Experiments show that our model achieves better performance on two publicly available population datasets (ETH and UCY).
多维时空融合行人轨迹预测
行人轨迹预测是自动驾驶中的一项关键技术。由于行人轨迹的多变性和相互作用的复杂性,有效的时空特征提取和融合是关键。以往的研究大多没有明确考虑行人之间相互作用的趋势,这有助于模型关注对预测目标未来运动影响较大的邻近行人。为了解决这个问题,我们提出了一个多维时空融合图注意力网络,称为MST-G。具体来说,有向图被用来模拟行人之间的相互作用。同时,在利用时空卷积获取具有交互作用的轨迹特征的基础上,加入边缘卷积提取交互作用的时间连续性。最后,利用LSTM编解码器生成轨迹。实验表明,我们的模型在两个公开可用的人口数据集(ETH和UCY)上取得了更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信