Data underlying the MSc Thesis: Toward Occlusion Capable Human Trajectory Prediction

Here are the dataset and model files related to the MSc thesis: Toward Occlusion Capable Human Trajectory Prediction.This thesis focuses on handling occlusions and partially missing positional information of agents when predicting their trajectories.<br>Dataset files comprise three distinct versions of the trajectory dataset used throughout the thesis project:train, val and test splits for the trajectory dataset under <em>fully observed</em> conditionstrain, val and test splits for the trajectory dataset under <em>occluded</em> conditionstest split for the trajectory dataset under occluded conditions, with <em>imputation </em>of missing positions by means of interpolation and constant velocity extrapolation.Occluded trajectories were generated by applying a simulator of occlusion events onto a publicly available trajectory dataset: the Stanford Drone Dataset. Our dataset Files are therefore derived from the Stanford Drone Dataset.<br>Model files contain checkpoints with weights that can be used to initialize prediction models from our implementation. These checkpoints are accompanied by some metadata, with information about the evolution of train and validation losses throughout the training process of individual model instances. Models are trained in two separate phases (<em>I</em>, and <em>II</em>): each model file contains all relevant model data for both phases of one model instance.<br>The source code related to these files is hosted on this GitHub page. The repository's README contains a comprehensive set of instructions on how to use the files in order to reproduce the results we obtained in our research (please refer to the section titled "Downloading Models and Legacy Datasets").

本数据集与模型文件均关联于硕士学位论文《面向遮挡场景的人类轨迹预测》（Toward Occlusion Capable Human Trajectory Prediction）。该论文聚焦于智能体轨迹预测任务中，如何处理遮挡以及部分位置信息缺失的问题。
数据集文件包含本论文研究中使用的轨迹数据集的三个不同版本：完全观测（fully observed）条件下的轨迹数据集训练集、验证集与测试集；遮挡（occluded）条件下的轨迹数据集训练集、验证集与测试集；以及采用插值与匀速外推法对缺失位置进行补全（imputation）的遮挡条件下轨迹数据集测试集。
遮挡轨迹是通过将遮挡事件模拟器应用于公开可用的斯坦福无人机数据集（Stanford Drone Dataset）生成的，因此本数据集文件均衍生自斯坦福无人机数据集。
模型文件包含可用于初始化本研究实现的预测模型的权重检查点，这些检查点附带部分元数据，记录了单个模型实例在训练全过程中训练损失与验证损失的变化情况。模型分为两个独立训练阶段（阶段I与阶段II），每个模型文件均包含单个模型实例两个训练阶段的全部相关数据。
本数据集与模型相关的源代码托管于该GitHub页面，仓库的README文件包含了完整的操作指南，可用于复现本研究获得的实验结果（请参阅标题为"下载模型与遗留数据集"的章节）。