Abstract
Pedestrian trajectory prediction is fundamental to a wide range of scientific research work and industrial applications. Most of the current advanced trajectory prediction methods incorporate context information such as pedestrian neighbourhood, labelled static obstacles, and the background scene into the trajectory prediction process. In contrast to these methods which require rich contexts, the method in our paper focuses on predicting a pedestrian's future trajectory using his/her observed part of the trajectory only. Our method, which we refer to as LVTA, is a Location-Velocity-Temporal Attention LSTM model where two temporal attention mechanisms are applied to the hidden state vectors from the location and velocity LSTM layers. In addition, a location-velocity attention layer embedded inside a tweak module is used to improve the predicted location and velocity coordinates before they are passed to the next time step. Extensive experiments conducted on three large benchmark datasets and comparison with eleven existing trajectory prediction methods demonstrate that LVTA achieves competitive prediction performance. Specifically, LVTA attains 9.19 pixels Average Displacement Error (ADE) and 17.28 pixels Final Displacement Error (FDE) for the Central Station dataset, and 0.46 metres ADE and 0.92 metres FDE for the ETH&UCY datasets. Furthermore, evaluation on using LVTA to generate trajectories of different prediction lengths and on new scenes without the need of retraining confirms that it has good generalizability.
Highlights
Trajectory prediction is essential for a wide range of applications such as forecasting trajectories of vulnerable road users in traffic environments [1] and location based services [2], [3]
We focus on three hyperparameters that are crucial to the performance of the proposed trajectory prediction method: the dropout rate, the hidden dimension Nh of the long short-term memory (LSTM) layers, and the embedding dimension Ne of the embedding layers
3) METHODS BEING COMPARED We compare the performance of our LVTA method as well as its four variants against 12 methods listed below: Linear, Social Force Model (SFM) [5], Linear Trajectory Avoidance (LTA) [6], Behaviour Convolutional Neural Networks (CNNs) [32], Vanilla LSTM, Social-Aware Generative Adversarial Imitation Learning (SA-GAIL) [25], Social-LSTM [11], Attention-LSTM [47], SGAN [22], Nikhil and Morris [14], Liang et al [21], and SR-LSTM [20]
Summary
Trajectory prediction is essential for a wide range of applications such as forecasting trajectories of vulnerable road users in traffic environments [1] and location based services [2], [3]. It is an important component for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles [4]. One way to predict pedestrians’ trajectories in a scene is to model the physics of the human movement patterns. Methods that were proposed prior to 2015 follow the SFM method by exploring the physical aspects of crowd movement; for instance, by minimizing collisions among pedestrians [6], by modelling the
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
