Enhancing Trajectory Prediction using Sparse Outputs: Application to Team Sports

  title={Enhancing Trajectory Prediction using Sparse Outputs: Application to Team Sports},
  author={Brandon Victor and Aiden Nibali and Zhen He and David L. Carey},
  journal={Neural Comput. Appl.},
Sophisticated trajectory prediction models that effectively mimic team dynamics have many potential uses for sports coaches, broadcasters and spectators. However, through experiments on soccer data we found that it can be surprisingly challenging to train a deep learning model for player trajectory prediction which outperforms linear extrapolation on average distance between predicted and true future trajectories. We propose and test a novel method for improving training by predicting a sparse… 

Figures and Tables from this paper


Diverse Generation for Multi-Agent Sports Games
A new generative model for multi-agent trajectory data, focusing on the case of multi-player sports games, that leverages graph neural networks and variational recurrent neural networks to achieve a permutation equivariant model suitable for sports.
Social LSTM: Human Trajectory Prediction in Crowded Spaces
This work proposes an LSTM model which can learn general human movement and predict their future trajectories and outperforms state-of-the-art methods on some of these datasets.
Generating Multi-Agent Trajectories using Programmatic Weak Supervision
This work presents a hierarchical framework that can effectively learn sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay, and is inspired by recent work on leveraging programmatically produced weak labels, which it extends to the spatiotemporal regime.
RED: A Simple but Effective Baseline Predictor for the TrajNet Benchmark
It is shown how a Recurrent-Encoder with a Dense layer stacked on top, referred to as RED-predictor, is able to achieve top-rank at the TrajNet 2018 challenge compared to elaborated models.
Interactive Sports Analytics
This article presents an intelligent human--computer interface that utilizes trajectories instead of words, which enables specific play retrieval in sports and significantly improves the retrieval quality.
Particle-based Pedestrian Path Prediction using LSTM-MDL Models
A combination of particle filtering strategies and a LSTM-MDL model is proposed to address a multimodal path prediction task, yielding the counter-intuitive result that the simplest approach performs best.
You'll never walk alone: Modeling social behavior for multi-target tracking
A model of dynamic social behavior, inspired by models developed for crowd simulation, is introduced, trained with videos recorded from birds-eye view at busy locations, and applied as a motion model for multi-people tracking from a vehicle-mounted camera.
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
The proposed Deep Stochastic IOC RNN Encoder-decoder framework, DESIRE, for the task of future predictions of multiple interacting agents in dynamic scenes significantly improves the prediction accuracy compared to other baseline methods.
An LSTM network for highway trajectory prediction
This article presents a first step towards consistent trajectory prediction by introducing a long short-term memory (LSTM) neural network, which is capable of accurately predicting future longitudinal and lateral trajectories for vehicles on highway.
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
A recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people, and outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.