Overview

This repo provides the code of Neuromorphic Imaging and Classification with Graph Learning.

@article{zhang2024neuromorphic,
  title    =  {Neuromorphic Imaging and Classification with Graph Learning},
  author   =  {Pei Zhang and Chutian Wang and Edmund Y. Lam},
  journal  =  {Neurocomputing},
  volume   =  {565},
  pages    =  {127010(1--9)},
  month    =  {January},
  year     =  {2024},
  doi      =  {10.1016/j.neucom.2023.127010},
}

Find more Neuromorphic Imaging achievements from our group: HKU Imaging Systems Laboratory.

Dataset

1. N-CARS: https://www.prophesee.ai/2018/03/13/dataset-n-cars/
2. N-MNIST: https://www.garrickorchard.com/datasets/n-mnist
3. ASL-DVS: https://github.com/PIX2NVS/NVS2Graph
4. KTH Dataset: https://www.csc.kth.se/cvap/actions/

Download our SN-KTH (password: zhang2024neuromorphic):

To simulate your own SN-KTH, please refer to v2e or PIX2NVS.

Implementation

Dependencies

torch
torch_geometric
numpy
scipy
dv
psee_loader (https://github.com/prophesee-ai/prophesee-automotive-dataset-toolbox/tree/master)

Usage

• We currently offer the core code only. Hopefully it already helps.
• Training & Testing code will be released in the near future. Stay tuned for updates!

Acknowledgement

Thank NVS2Graph for code reference.