OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets
This work addresses benchmarking challenges for researchers in human trajectory prediction, but it is incremental as it focuses on dataset analysis rather than new prediction methods.
The paper tackles the problem of evaluating dataset complexity for human trajectory prediction by defining indicators around predictability, regularity, and context complexity, and compares common datasets to inform benchmarking.
Human Trajectory Prediction (HTP) has gained much momentum in the last years and many solutions have been proposed to solve it. Proper benchmarking being a key issue for comparing methods, this paper addresses the question of evaluating how complex is a given dataset with respect to the prediction problem. For assessing a dataset complexity, we define a series of indicators around three concepts: Trajectory predictability; Trajectory regularity; Context complexity. We compare the most common datasets used in HTP in the light of these indicators and discuss what this may imply on benchmarking of HTP algorithms. Our source code is released on Github.