InhwanBae/EigenTrajectory

Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"

38
/ 100
Emerging

This project helps improve the accuracy of predicting where pedestrians will move next. It takes historical movement data of people and generates a compact representation of their motion, which then feeds into existing prediction models. The output is a significantly more accurate and reliable forecast of future pedestrian paths, making it useful for urban planners, autonomous vehicle developers, or crowd management professionals.

106 stars. No commits in the last 6 months.

Use this if you need to improve the prediction accuracy of existing pedestrian trajectory forecasting models using a more efficient data representation.

Not ideal if you are looking for a completely new trajectory prediction model from scratch, as this project focuses on enhancing existing ones.

pedestrian-movement urban-planning autonomous-vehicles crowd-management trajectory-forecasting
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

106

Forks

8

Language

Python

License

MIT

Last pushed

Jun 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/InhwanBae/EigenTrajectory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.