TKDE 2021 Paper

DeepCrowd: A Deep Model for Large-Scale Citywide Crowd Density and Flow Prediction

Datasets

Yahoo! Bousai Crowd Data is now available at Yahoo! Japan Research website. <br> https://randd.yahoo.co.jp/en/softwaredata

• Please fill in Application PDF for Use of Yahoo! Bousai Crowd Data.
• Send it to yjresearch-data “at” mail.yahoo.co.jp.
• https://s.yimg.jp/dl/research_lab/randd/software_data/application_form_YJ21_10042184_en.pdf
• See the sample PDF ./YahooBousaiCrowdData/application_form_YJ21_10042184_en_sample.pdf.
• The fields below the underline on the application form do not need to be filled in.
• If there is any issue, please kindly ask Kota Tsubouchi ktsubouc@yahoo-corp.jp about the data access.

Model

Please check DeepCrowd.py or workBousaiTYO(OSA)_ours.

Dependencies

Working environment and major dependencies:

• Ubuntu 16.04.6 LTS
• Python 3 (>= 3.5; Anaconda Distribution)
• NumPy (>= 1.11.0)
• pandas (>= 0.18.0)
• TensorFlow/tensorflow-gpu (= 1.1x.0)
• Keras (>= 2.0.8)

Citation

If you find anything in this repository useful to your research, please cite our paper :) We sincerely appreciate it. DeepCrowd: A Deep Model for Large-Scale Citywide Crowd Density and Flow Prediction

@article{jiang2021deepcrowd,
  title={DeepCrowd: A Deep Model for Large-Scale Citywide Crowd Density and Flow Prediction},
  author={Jiang, Renhe and Cai, Zekun and Wang, Zhaonan and Yang, Chuang and Fan, Zipei and Chen, Quanjun and Tsubouchi, Kota and Song, Xuan and Shibasaki, Ryosuke},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  year={2021},
  publisher={IEEE}
}