Embedding group and obstacle information in LSTM networks for human trajectory prediction in crowded scenes

Niccolo Bisagno; Cristiano Saltori; Bo Zhang; Francesco G.B. De Natale; Nicola Conci

首页> 外文期刊>Computer vision and image understanding >Embedding group and obstacle information in LSTM networks for human trajectory prediction in crowded scenes

【24h】

Embedding group and obstacle information in LSTM networks for human trajectory prediction in crowded scenes

机译：在LSTM网络中嵌入组和障碍信息，用于拥挤场景中的人类轨迹预测

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Recurrent neural networks have shown good abilities in learning the spatio-temporal dependencies of moving agents in crowded scenes. Recently, they have been adopted to predict the motion of pedestrians by learning the relative motion of each individual in the crowd with respect to its neighbors. Crowded scenes present a wide variety of situations, which do not depend solely on the agents' positions, but also relate to the structure of the environment, the density of the crowd, and the social relationships between pedestrians. In this work we propose a framework to improve the state-of-the-art models of crowd motion prediction by enriching the learning model with the social relationships between pedestrians walking in the crowd, as well as the layout of the environment. We observe that socially-related people tend to exhibit coherent motion patterns. Exploiting the motion coherency, we are able to cluster trajectories with similar motion properties and improve the trajectory prediction, especially at the group level. Furthermore, we incorporate into the model also the layout of the environment, to guarantee a more realistic and reliable learning framework. We evaluate our approach on standard crowd benchmark datasets, demonstrating its efficacy and applicability, improving the accuracy in trajectory prediction.

机译：经常性的神经网络在学习在拥挤的场景中学习移动代理的时空依赖性具有良好的能力。最近，他们已被采用来预测行人的行动，通过了解人群中的每个人的相对运动以及邻国。拥挤的场景存在各种各样的情况，这些情况并不依赖于代理商的立场，而且还涉及环境的结构，人群的密度以及行人之间的社会关系。在这项工作中，我们提出了一个框架，通过丰富与人群中行走的行人之间的社会关系以及环境的布局来改善人群运动预测的最先进模式。我们观察到社会相关的人倾向于表现出相干的运动模式。利用运动一致性，我们能够在具有类似运动特性的群集轨迹并改善轨迹预测，尤其是在组级别。此外，我们也将模型纳入了环境的布局，以保证更现实和可靠的学习框架。我们评估了我们在标准人群基准数据集中的方法，证明了其功效和适用性，提高了轨迹预测的准确性。

著录项

来源
《Computer vision and image understanding》 |2021年第2期|103126.1-103126.9|共9页
作者
Niccolo Bisagno; Cristiano Saltori; Bo Zhang; Francesco G.B. De Natale; Nicola Conci;
展开▼
作者单位

Deportment of Information Engineering and Computer Science - DISI University of Trento 38123 Italy;

Deportment of Information Engineering and Computer Science - DISI University of Trento 38123 Italy;

Department of Intelligence Science and Technology College of Information Science and Technology Dalian Maritime University 116026 China;

Deportment of Information Engineering and Computer Science - DISI University of Trento 38123 Italy;

Deportment of Information Engineering and Computer Science - DISI University of Trento 38123 Italy;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Trajectory prediction; Group; Obstacle; LSTM-based;

机译：轨迹预测;团体;障碍;LSTM为基础;

Embedding group and obstacle information in LSTM networks for human trajectory prediction in crowded scenes

摘要

著录项

相关主题

期刊订阅