AC-VRNN: Attentive Conditional-VRNN for multi-future trajectory prediction

• Published in: Computer vision and image understanding Vol. 210; p. 103245
• Main Authors: Bertugli, Alessia, Calderara, Simone, Coscia, Pasquale, Ballan, Lamberto, Cucchiara, Rita
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2021
• Subjects: Graph attention networks; Multi-future prediction; Time series; Trajectory forecasting; Variational recurrent neural networks; Trajectory forecasting; Graph attention networks; Variational recurrent neural networks; Multi-future prediction; Time series
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2021.103245

Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently multi-modal nature of human paths which makes socially acceptable multiple futures when human interactions are involved. To this end, we propose a generative architecture for multi-future trajectory predictions based on Conditional Variational Recurrent Neural Networks (C-VRNNs). Conditioning mainly relies on prior belief maps, representing most likely moving directions and forcing the model to consider past observed dynamics in generating future positions. Human interactions are modelled with a graph-based attention mechanism enabling an online attentive hidden state refinement of the recurrent estimation. To corroborate our model, we perform extensive experiments on publicly-available datasets (e.g., ETH/UCY, Stanford Drone Dataset, STATS SportVU NBA, Intersection Drone Dataset and TrajNet++) and demonstrate its effectiveness in crowded scenes compared to several state-of-the-art methods. •Multi-future trajectory predictions in crowded scenarios are considered.•We propose a model based on Conditional Variational Recurrent Neural Networks.•Prior belief maps steer predictions mimicking human behaviours.•An attentive-based graph neural network models interactions among pedestrians.•We outperform state-of-the-art methods on several trajectory prediction benchmarks.