InhwanBae/DMRGCN

Official Code for "Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction (AAAI 2021)"

34
/ 100
Emerging

This project helps predict the future paths of pedestrians in crowded environments, which is crucial for applications like autonomous vehicles or crowd management. It takes in past pedestrian movement data and outputs probable future trajectories, considering how people interact with each other. This tool is for researchers and engineers working on intelligent systems that need to understand and anticipate human movement patterns.

No commits in the last 6 months.

Use this if you need to accurately predict pedestrian trajectories in complex, interactive scenarios while accounting for social dynamics and potential changes in direction.

Not ideal if you are looking for a simple, off-the-shelf solution for general object tracking or if your prediction needs do not involve understanding social interactions between multiple agents.

pedestrian-prediction autonomous-driving crowd-simulation human-robot-interaction smart-city-planning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

29

Forks

3

Language

Python

License

MIT

Last pushed

Jul 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/InhwanBae/DMRGCN"

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