peterzs / sap

Code for Towards Streaming Perception (ECCV 2020)

sAP — Code for Towards Streaming Perception

This repo contains code for our ECCV 2020 paper (Towards Streaming Perception). sAP stands for streaming Average Precision.

The dataset used in this project (Argoverse-HD) can be found on the project page.

Contents

• Offline detection
• Streaming (real-time online) detection
• Streaming tracking & forecasting (Coming soon!)
• Simulated streaming detection, tracking, & forecasting (Coming soon!)
• Simulated streaming detection, tracking, & forecasting with infinite GPUs (Coming soon!)
• Meta-detector Streamer (Coming soon!)
• Streaming evaluation
• Single-frame schedule simulator
• Helper functions for visualization (Coming soon!)

Getting started

1. Follow the instructions here to download and set up the dataset.
2. Follow the instructions here to install the dependencies.
3. Check out the examples to run different tasks in exp/*.

Citation

If you use the code or the data for your research, please cite the paper:

@article{Li2020StreamingP,
  title={Towards Streaming Perception},
  author={Li, Mengtian and Wang, Yuxiong and Ramanan, Deva},
  journal={ECCV},
  year={2020}
}

Acknowledgement

We would like to thank the mmdetection team for implementing so many different detectors in a single awesome repo with a unified interface! This greatly reduced our efforts to evaluate different detectors under our streaming setting.