## Introduction
Pedestrian detection technology has been developed very mature, but it is still a very big challenge to detect pedestrians in low light conditions. Although infrared light images can assist pedestrian detection, however, in most scenes, only visible light images are available. Therefore, we organized this competition to promote the research of pedestrian detection in low light conditions.

## Dataset
The dataset used in this competition contains 15030 visible light images(11782 images for training and 3248 for testing), it is a subset of our previous work: [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://arxiv.org/abs/2108.10831). In low light conditions, even the human eye can hardly distinguish pedestrians. Therefore, our pedestrian marking work is completed with the assistance of infrared light images.
## License
Our dataset is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications, or personal experimentation. Permission is granted to use the data given that you agree to our [license terms](https://github.com/bupt-ai-cz/LLVIP/blob/main/Term%20of%20Use%20and%20License.md).
If you use this data for your research, please cite our paper ：
```
@inproceedings{jia2021llvip,
  title={LLVIP: A Visible-infrared Paired Dataset for Low-light Vision},
  author={Jia, Xinyu and Zhu, Chuang and Li, Minzhen and Tang, Wenqi and Zhou, Wenli},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={3496--3504},
  year={2021}
}
```
## Contact
If you encounter any problems please post them in the [Discussion](https://www.kaggle.com/c/find-person-in-the-dark/discussion) column without hesitation, or contact us directly by the following email:
- shengjie.Liu@bupt.edu.cn
- czhu@bupt.edu.cn
## Related
If you like our 'Find Person in the Dark' Dataset, you will probably be interested in our other researches, please visit [here](https://github.com/bupt-ai-cz) for more details.