The Stanford Drone Dataset Is More Complex Than We Think: An Analysis of Key Characteristics
The Stanford Drone Dataset Is More Complex Than We Think: An Analysis of Key Characteristics
复制标题
DOI：
10.1109/tiv.2022.3166642
复制
发表时间：
2022-03
影响因子：
8.2
通讯作者：
Joshua Andle;Nicholas Soucy;Simon Socolow;S. Y. Sekeh
中科院分区：
文献类型：
--
作者：
Joshua Andle;Nicholas Soucy;Simon Socolow;S. Y. Sekeh
存在几个数据集，其中包含个人轨迹的注释信息。这些数据集对于许多现实世界的应用至关重要，包括轨迹预测和自主导航。目前使用的一个突出的数据集是斯坦福大学无人机数据集（SDD）（Robicquet et al.，2016年）。尽管它的突出，围绕这个数据集的特点的讨论是不够的。我们展示了这种不足如何减少用户可用的信息，并可能影响性能。我们的贡献包括概述SDD中的关键特征，采用信息理论测量和自定义度量来清晰地可视化这些特征，PECNet的实现（Mangalam等人，2020）和Y-Net（Mangalam等人，2021）轨迹预测模型，以证明概述的特征对预测性能的影响，最后我们提供了SDD和交叉无人机（inD）数据集之间的比较。我们对SDD关键特征的分析是重要的，因为如果没有关于可用数据集的足够信息，用户选择最适合其方法的数据集、复制彼此的结果以及解释自己的结果的能力就会受到阻碍。我们通过这种分析所做的观察为那些计划使用SDD的人提供了一个容易获得和解释的信息来源。我们的目的是提高应用于该数据集的方法的性能和可重复性，同时为新用户清楚地详细说明数据集不太明显的特征。
Several datasets exist which contain annotated information of individuals’ trajectories. Such datasets are vital for many real-world applications, including trajectory prediction and autonomous navigation. One prominent dataset currently in use is the Stanford Drone Dataset (SDD) (Robicquet et al., 2016). Despite its prominence, discussion surrounding the characteristics of this dataset is insufficient. We demonstrate how this insufficiency reduces the information available to users and can impact performance. Our contributions include the outlining of key characteristics in the SDD, employment of an information-theoretic measure and custom metric to clearly visualize those characteristics, the implementation of the PECNet (Mangalam et al., 2020) and Y-Net (Mangalam et al., 2021) trajectory prediction models to demonstrate the outlined characteristics’ impact on predictive performance, and lastly we provide a comparison between the SDD and Intersection Drone (inD) Dataset. Our analysis of the SDD’s key characteristics is important because without adequate information about available datasets a user’s ability to select the most suitable dataset for their methods, to reproduce one another’s results, and to interpret their own results are hindered. The observations we make through this analysis provide a readily accessible and interpretable source of information for those planning to use the SDD. Our intention is to increase the performance and reproducibility of methods applied to this dataset going forward, while also clearly detailing less obvious features of the dataset for new users.