AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction

Abstract

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 modeled 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.

Accepted at Computer Vision and Image Understanding (CVIU)

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• Learning Deep Embeddings with Histogram Loss
• Stochastic Prediction of Multi-Agent Interactions from Partial Observations
• Neural Relational Inference with Fast Modular Meta-learning
• Factorised Neural Relational Inference for Multi-Interaction Systems
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• BasketballGAN: Generating Basketball Play Simulation Through Sketching

Cited by in corpus (4)

• A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions
• Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
• FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation
• From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video