DeepTrack: Lightweight Deep Learning for Vehicle Trajectory Prediction in Highways

Vinit Katariya, Mohammadreza Baharani, Nichole Morris, Omidreza Shoghli, Hamed Tabkhi

Research output: Contribution to journalArticlepeer-review

Abstract

Vehicle trajectory prediction is essential for enabling safety-critical intelligent transportation systems (ITS) applications used in management and operations. While there have been some promising advances in the field, there is a need for modern deep learning algorithms that allow real-time trajectory prediction on embedded IoT devices. This article presents DeepTrack, a novel deep learning algorithm customized for real-time vehicle trajectory prediction and monitoring applications in arterial management, freeway management, traffic incident management, and work zone management for high-speed incoming traffic. In contrast to previous methods, the vehicle dynamics are encoded using Temporal Convolutional Networks (TCNs) to provide more robust time prediction with less computation. DeepTrack also uses depthwise convolution, which reduces the complexity of models compared to existing approaches in terms of model size and operations. Overall, our experimental results demonstrate that DeepTrack achieves comparable accuracy to state-of-the-art trajectory prediction models but with smaller model sizes and lower computational complexity, making it more suitable for real-world deployment.

Original languageEnglish (US)
Pages (from-to)18927-18936
Number of pages10
JournalIEEE Transactions on Intelligent Transportation Systems
Volume23
Issue number10
DOIs
StatePublished - Oct 1 2022

Bibliographical note

Publisher Copyright:
© 2000-2011 IEEE.

Keywords

  • DeepTrack
  • Vehicle trajectory prediction
  • deep learning
  • temporal convolutions

Fingerprint

Dive into the research topics of 'DeepTrack: Lightweight Deep Learning for Vehicle Trajectory Prediction in Highways'. Together they form a unique fingerprint.

Cite this