Bi-Prediction: Pedestrian Trajectory Prediction Based on Bidirectional LSTM Classification

Research output: Chapter in Book/Conference paperConference paperpeer-review

33 Citations (Web of Science)

Abstract

Pedestrian trajectory prediction is important in various applications such as driverless vehicles, social robots, intelligent tracking systems and space planning. Existing methods focus on analysing the influence of neighbours but ignore the effect of the intended destinations of pedestrians which also
plays a key role in route planning. In this paper, we propose a novel two-stage trajectory prediction method to yield multiple prediction trajectories with different probabilities towards different destination regions in the scene. Our method, which we refer to as Bi-Prediction, uses a bidirectional LSTM architecture to automatically classify trajectories into a small number of
route classes before trajectory prediction. We have evaluated our method against two baseline methods and three state-of-art methods on two benchmark datasets. Our experimental results show that the extra classification stage improves the accuracy of the predicted trajectories.
Original languageEnglish
Title of host publication2017 International Conference on Digital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2017, Sydney, Australia, November 29 - December 1, 2017
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781538628393
Publication statusPublished - 2017
Event2017 International Conference on Digital Image Computing: Techniques and Applications - Sydney, Australia
Duration: 29 Nov 20171 Dec 2017

Conference

Conference2017 International Conference on Digital Image Computing: Techniques and Applications
Abbreviated titleDICTA
Country/TerritoryAustralia
CitySydney
Period29/11/171/12/17

Fingerprint

Dive into the research topics of 'Bi-Prediction: Pedestrian Trajectory Prediction Based on Bidirectional LSTM Classification'. Together they form a unique fingerprint.

Cite this