The offical implementation for the "NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination" which is published in ACM MM 2020.
We propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood.
This work has won the first place at the CrowdHuman Challenge, 2020.
- This repo is implemented based on detectron2.
| Model | Backbone | AP | Recall | MR | Weights |
|---|---|---|---|---|---|
| Faster RCNN | ResNet-50 | 85.0 | 87.5 | 44.5 | faster_rcnn_model_final.pth |
| NOH-NMS | ResNet-50 | 88.8 | 92.6 | 43.7 | noh_nms_model_final.pth |
Download the CrowdHuman Datasets from http://www.crowdhuman.org/, and then move them under the directory like:
./data/crowdhuman
├── annotations
│ └── annotation_train.odgt
│ └── annotation_val.odgt
├── images
│ └── train
│ └── val
cd detectron2
pip install -e .
#or rebuild
sh build.sh
See GETTING_STARTED.md in detectron2
if you find this project useful for your research, please cite:
@inproceedings{zhou2020noh,
title={NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination},
author={Zhou, Penghao and Zhou, Chong and Peng, Pai and Du, Junlong and Sun, Xing and Guo, Xiaowei and Huang, Feiyue},
booktitle={Proceedings of the 28th ACM International Conference on Multimedia},
pages={1967--1975},
year={2020}
}