This repository contains the code for unsupervised group estimation applied to the trajectory prediction models.
Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
Inhwan Bae,
Jin-Hwi Park, and
Hae-Gon Jeon
Accepted to
ECCV 2022
- Learns to assign each pedestrian into the most likely behavior group in an unsupervised manner.
- Pedestrian group pooling&unpooling and group hierarchy graph for group behavior modeling.
- Group-level latent vector sampling strategy to share the latent vector between group members.
Environment
All models were trained and tested on Ubuntu 20.04 with Python 3.7 and PyTorch 1.9.0 with CUDA 11.1.
Dataset
Preprocessed ETH and UCY datasets are included in this repository, under ./dataset/
.
The train/validation/test splits are the same as those fond in Social-GAN.
Baseline models
This repository supports the SGCN baseline trajectory predictor.
We have included model source codes from their official GitHub in model_baseline.py
To train our GPGraph-SGCN on the ETH and UCY datasets at once, we provide a bash script train.sh
for a simplified execution.
./train.sh
We provide additional arguments for experiments:
./train.sh -t <experiment_tag> -d <space_seperated_dataset_string> -i <space_seperated_gpu_id_string>
# Examples
./train.sh -d "hotel" -i "1"
./train.sh -t onescene -d "hotel" -i "1"
./train.sh -t allinonegpu -d "eth hotel univ zara1 zara2" -i "0 0 0 0 0"
If you want to train the model with custom hyper-parameters, use train.py
instead of the script file.
We have included pretrained models in the ./checkpoints/
folder.
You can use test.py
to evaluate our GPGraph-SGCN model.
python test.py
If you find this code useful for your research, please cite our papers :)
DMRGCN (AAAI'21)
|
NPSN (CVPR'22)
|
GP-Graph (ECCV'22)
|
Graph-TERN (AAAI'23)
@inproceedings{bae2022gpgraph,
title={Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction},
author={Bae, Inhwan and Park, Jin-Hwi and Jeon, Hae-Gon},
booktitle={Proceedings of the European Conference on Computer Vision},
year={2022}
}
More Information (Click to expand)
@article{bae2021dmrgcn,
title={Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction},
author={Bae, Inhwan and Jeon, Hae-Gon},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
year={2021}
}
@inproceedings{bae2022npsn,
title={Non-Probability Sampling Network for Stochastic Human Trajectory Prediction},
author={Bae, Inhwan and Park, Jin-Hwi and Jeon, Hae-Gon},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2022}
}
@article{bae2023graphtern,
title={A Set of Control Points Conditioned Pedestrian Trajectory Prediction},
author={Bae, Inhwan and Jeon, Hae-Gon},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
year={2023}
}
Part of our code is borrowed from SGCN. We thank the authors for releasing their code and models.