# Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets

## TL;DR

This paper introduces MX-LSTM, a joint model for predicting pedestrian trajectories and head poses by leveraging the correlation between movement and head orientation, improving long-term forecasting especially in slow-moving scenarios.

## Contribution

The paper presents MX-LSTM, a novel joint LSTM model that captures the interplay between trajectories and head poses using full covariance matrices during training.

## Key findings

- Outperforms state-of-the-art on public benchmarks.
- Effective in slow-moving pedestrian scenarios.
- Provides accurate long-term predictions.

## Abstract

In this work, we explore the correlation between people trajectories and their head orientations. We argue that people trajectory and head pose forecasting can be modelled as a joint problem. Recent approaches on trajectory forecasting leverage short-term trajectories (aka tracklets) of pedestrians to predict their future paths. In addition, sociological cues, such as expected destination or pedestrian interaction, are often combined with tracklets. In this paper, we propose MiXing-LSTM (MX-LSTM) to capture the interplay between positions and head orientations (vislets) thanks to a joint unconstrained optimization of full covariance matrices during the LSTM backpropagation. We additionally exploit the head orientations as a proxy for the visual attention, when modeling social interactions. MX-LSTM predicts future pedestrians location and head pose, increasing the standard capabilities of the current approaches on long-term trajectory forecasting. Compared to the state-of-the-art, our approach shows better performances on an extensive set of public benchmarks. MX-LSTM is particularly effective when people move slowly, i.e. the most challenging scenario for all other models. The proposed approach also allows for accurate predictions on a longer time horizon.