Human Trajectory Completion with Transformers
Human Trajectory Completion with Transformers
复制标题
DOI：
10.1109/icc45855.2022.9838743
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Junwei Ma;Chao Yang;S. Mao;Jian Zhang;Senthilkumar C. G. Periaswamy;J. Patton
中科院分区：
文献类型：
--
作者：
Junwei Ma;Chao Yang;S. Mao;Jian Zhang;Senthilkumar C. G. Periaswamy;J. Patton
随着新冠肺炎疫情的爆发，接触者追踪已成为一个重要问题。事实证明，保持社交距离和隔离感染者对遏制新冠肺炎的传播非常有益，这都取决于确定人们的轨迹。然而，目前基于访谈的方法成本很高，现有的基于移动应用程序的方案依赖于完整和准确的数据。在本文中，我们提出了一种基于变换编码器的方法，利用图组合拉普拉斯矩阵提取空间位置嵌入来插值不完整的人体轨迹。为了模拟人类轨迹，我们提出了一个图形嵌入模块来提取基于预定义位置集群的空间特征。首先将不完全轨迹序列预处理成矩阵，然后用于训练用于轨迹补全的深度变压器编码器网络。我们使用真实世界的低功耗蓝牙（BLE）数据集进行的实验验证了我们提出的方法的有效性，该方法优于几种基线方法。
With outbreak of the COVID-19 pandemic, contact tracing has become an important problem. It has been proven that maintaining social distance and isolating affected people are highly beneficial for curbing the spread of COVID-19, which all depend on identifying people’s trajectories. However, the current interview-based approach is costly, and the existing mobile app-based schemes rely on complete and accurate data. In this paper, we propose a transformer encoder-based approach with spatial position embedding extracted using a graph Combinatorial Laplacian matrix to interpolate incomplete human trajectories. To model human trajectory, we propose a graphical embedded module to extract spatial features based on predefined location clusters. The incomplete trajectory sequences are first preprocessed into matrices and then used to train a deep transformer encoder network for trajectory completion. Our experiments using a real world Bluetooth Low Energy (BLE) dataset validate the efficacy of our proposed approach, which outperforms several baseline methods.