Human Trajectory Forecasting in Crowds: A Deep Learning Perspective
This work addresses the need for better evaluation and modeling in human trajectory forecasting, which is crucial for applications like evacuation analysis and intelligent transport systems, but it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of human trajectory forecasting in crowds by proposing two knowledge-based data-driven methods and a new benchmark, TrajNet++, with novel metrics for socially acceptable trajectories, showing that their method outperforms baselines on real-world and synthetic datasets.
Since the past few decades, human trajectory forecasting has been a field of active research owing to its numerous real-world applications: evacuation situation analysis, deployment of intelligent transport systems, traffic operations, to name a few. Early works handcrafted this representation based on domain knowledge. However, social interactions in crowded environments are not only diverse but often subtle. Recently, deep learning methods have outperformed their handcrafted counterparts, as they learned about human-human interactions in a more generic data-driven fashion. In this work, we present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two knowledge-based data-driven methods to effectively capture these social interactions. To objectively compare the performance of these interaction-based forecasting models, we develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting. We propose novel performance metrics that evaluate the ability of a model to output socially acceptable trajectories. Experiments on TrajNet++ validate the need for our proposed metrics, and our method outperforms competitive baselines on both real-world and synthetic datasets.