Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction
This work addresses a gap in benchmarking for trajectory prediction, providing a tool to assess dataset complexity, which is incremental as it builds on existing methods for dataset representation.
The paper tackled the problem of quantifying the complexity of human trajectory prediction datasets by proposing a method based on spatial sequence alignment and learning vector quantization to measure information content, and applied it to several standard benchmarks to analyze their complexity.
Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models. In order to gain a better understanding of the complexity of trajectory prediction tasks and following the intuition, that more complex datasets contain more information, an approach for quantifying the amount of information contained in a dataset from a prototype-based dataset representation is proposed. The dataset representation is obtained by first employing a non-trivial spatial sequence alignment, which enables a subsequent learning vector quantization (LVQ) stage. A large-scale complexity analysis is conducted on several human trajectory prediction benchmarking datasets, followed by a brief discussion on indications for human trajectory prediction and benchmarking.