38 lines
2.5 KiB
Plaintext
38 lines
2.5 KiB
Plaintext
---
|
|
title: "Autoencoder Trajectory Compression"
|
|
tags: [deep-learning, recurrent-neural-networks, trajectory-analysis, data-compression, geoinformatics, autoencoders, LSTM, GPS]
|
|
excerpt: "LSTM autoencoder better DP for trajectory compression (Fréchet/DTW)."
|
|
teaser: /figures/23_trajectory_model.png
|
|
venue: "ICAART 2023"
|
|
---
|
|
|
|
The proliferation of location-aware mobile devices generates vast amounts of GPS trajectory data, necessitating efficient storage solutions. While various compression techniques aim to reduce data volume, preserving essential spatio-temporal information remains crucial.
|
|
|
|
<CenteredImage
|
|
src="/figures/23_trajectory_model.png"
|
|
alt="Schematic diagram of the LSTM autoencoder model architecture used for trajectory compression"
|
|
width={450}
|
|
height={450}
|
|
caption="Schematic of the LSTM Autoencoder Decoder Architecture."
|
|
/>
|
|
|
|
This paper introduces a novel approach for **compressing and reconstructing GPS trajectories** using a **Long Short-Term Memory (LSTM) autoencoder**. The autoencoder learns a compressed latent representation of the trajectory sequence, which can then be decoded to reconstruct the original path.
|
|
|
|
Our method was evaluated on two distinct datasets: one from a gaming context and another real-world dataset (T-Drive). We assessed performance across a range of compression ratios and trajectory lengths, comparing it against the widely used traditional **Douglas-Peucker algorithm**.
|
|
|
|
<FloatingImage
|
|
src="/figures/23_trajectory_scores.png"
|
|
alt="Graphs showing mean distance errors (e.g., Fréchet, DTW) for different compression ratios on the T-Drive dataset"
|
|
width={1000}
|
|
height={800}
|
|
float="right"
|
|
caption="Comparison of mean distance errors for different compression ratios on the T-Drive dataset."
|
|
/>
|
|
|
|
**Key findings:**
|
|
|
|
* The LSTM autoencoder approach significantly **outperforms Douglas-Peucker** in terms of reconstruction accuracy, as measured by both **discrete Fréchet distance** and **Dynamic Time Warping (DTW)**.
|
|
|
|
* Unlike point-reduction techniques like Douglas-Peucker, our method performs a **lossy reconstruction at every point** along the trajectory. This offers potential advantages in maintaining temporal resolution and providing greater flexibility for downstream analysis.
|
|
|
|
Experimental results demonstrate the effectiveness and potential benefits of using deep learning, specifically LSTM autoencoders, for GPS trajectory compression, offering improved accuracy over conventional geometric algorithms. <Cite bibtexKey="kolle2023compression" /> |