HSFM-\Σnn: Combining a Feedforward Motion Prediction Network and\n Covariance Prediction

2020/09/09 by Aleksey Postnikov, Postnikov, A., Aleksander Gamayunov +6
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition #Robotics (cs.RO) #Video Analysis and Summarization #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2009.04299

openalex publication_date 2020/09/09 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a new method for motion prediction:\nHSFM-\Σnn. Our proposed method combines two different approaches: a\nfeedforward network whose layers are model-based transition functions using the\nHSFM and a Neural Network (NN), on each of these layers, for covariance\nprediction. We will compare our method with classical methods for covariance\nestimation showing their limitations. We will also compare with a\nlearning-based approach, social-LSTM, showing that our method is more precise\nand efficient.\n

Citations

• Social force model for pedestrian dynamics

Related

• CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion
• CovarianceNet: Conditional Generative Model for Correct Covariance Prediction in Human Motion Prediction
• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
• Back to MLP: A Simple Baseline for Human Motion Prediction
• TrajectoryCNN: A New Spatio-Temporal Feature Learning Network for Human Motion Prediction