Particle-based pedestrian path prediction using LSTM-MDL models

TL;DR

This paper introduces a particle filter sampling method combined with LSTM-MDL models for multi-modal pedestrian path prediction, emphasizing the importance of considering multiple possible future paths in security applications.

Contribution

It proposes a novel combination of particle filtering with LSTM-MDL for multi-modal path prediction, and evaluates its effectiveness on synthetic and real-world data.

Findings

Simplest particle sampling approach performs best in tests.

The method is feasible for real-world scene analysis.

Multi-modal prediction improves risk assessment accuracy.

Abstract

Recurrent neural networks are able to learn complex long-term relationships from sequential data and output a pdf over the state space. Therefore, recurrent models are a natural choice to address path prediction tasks, where a trained model is used to generate future expectations from past observations. When applied to security applications, like predicting the path of pedestrians for risk assessment, a point-wise greedy (ML) evaluation of the output pdf is not feasible, since the environment often allows multiple choices. Therefore, a robust risk assessment has to take all options into account, even if they are overall not very likely. Towards this end, a combination of particle filter sampling strategies and a LSTM-MDL model is proposed to address a multi-modal path prediction task. The capabilities and viability of the proposed approach are evaluated on several synthetic test conditions, yielding the counter-intuitive result that the simplest approach performs best. Further, the feasibility of the proposed approach is illustrated on several real world scenes.