DeepTrack: Lightweight Deep Learning for Vehicle Path Prediction in Highways

TL;DR

DeepTrack is a lightweight deep learning model utilizing Temporal Convolutional Networks and depthwise convolution to enable real-time vehicle trajectory prediction on embedded devices, suitable for various traffic management applications.

Contribution

The paper introduces DeepTrack, a novel, efficient deep learning algorithm that encodes vehicle dynamics with TCNs and reduces complexity with depthwise convolution for real-time traffic prediction.

Findings

Achieves comparable accuracy to state-of-the-art models.

Has smaller model size and lower computational complexity.

Suitable for deployment on embedded IoT devices.

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.