Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction

TL;DR

This paper introduces a novel method to quantify the complexity of human trajectory datasets by using a prototype-based representation and information measures, aiding better benchmarking of prediction models.

Contribution

It proposes a new approach combining spatial sequence alignment and learning vector quantization to measure dataset complexity in trajectory prediction tasks.

Findings

Complexity varies across benchmark datasets.

The method reveals insights into dataset informativeness.

Implications for model benchmarking and development.

Abstract

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.