NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset, BMVC 2021

Igor Morawski, Yu-An Chen, Yu-Sheng Lin, Winston H. Hsu

We present a high-quality large-scale dataset of outdoor images targeting low-light object detection. The dataset contains more than 7K images and 46K annotated objects (with bounding boxes) that belong to classes: person, bicycle, and car. The photos were taken on the streets at evening hours, and thus all images present low-light conditions to a varying degree of severity. We used two DSLR cameras to capture the scenes: Sony RX100 VII and Nikon D750, and throughout the paper, we refer to the sets collected by these cameras as Sony and Nikon (data)set. We show the statistics of our dataset in the table below.

If you find our dataset useful in your research or publication, please cite our work (accepted to BMVC 2021):

@misc{morawski2021nod,
      title={NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset}, 
      author={Igor Morawski and Yu-An Chen and Yu-Sheng Lin and Winston H. Hsu},
      year={2021},
      eprint={2110.10364},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Igor Morawski: e-mail, LinkedIn.

This work was supported in part by the Ministry of Science and Technology, Taiwan, under Grant MOST 110-2634-F-002-026 and Qualcomm Technologies, Inc. We are grateful to the National Center for High-performance Computing.