2022 AI City Challenge

AI City means applying AI to improve the efficiency of operations in city environments. This manifests itself in improving transportation outcomes by making traffic more efficient and making roads safer, improving building operations by making them more energy efficient, reducing friction in retail environments by speeding up traffic at retail checkout, etc. The common thread in all these diverse uses of AI is the extraction of actionable insights from a plethora of sensors through real-time streaming and batch analytics of the vast volume and flow of sensor data, such as those from cameras. The AI City Challenge Workshop at CVPR 2022 will specifically focus on problems in two domains where there is tremendous unlocked potential at the intersection of computer vision and artificial intelligence – The Intelligent Traffic Systems (ITS), and the brick and mortar retail business.

Problems of interest in ITS include:

City-scale multi-camera vehicle tracking
Natural language-based vehicle track retrieval
Naturalistic driver data analytics
Anomaly Detection

Problems of interest in retail stores include:

Automated checkout
Efficient Store utilization

We solicit original contributions in these and related areas where computer vision, natural language processing, and deep learning have shown promise in achieving large-scale practical deployment that will help make our environments smarter and safer.

To accelerate the research and development of techniques, the 6th edition of this Challenge will push the research and development in multiple directions. We will add a brand new track and dataset around naturalistic driving analysis where the data will be captured by several cameras mounted inside the vehicle and focus on driver safety and the task will be to classify driver actions. We will also add a new track evaluating the accuracy of retail store automated checkout using only computer vision sensors. To this end, we will release labeled data for various views of typical retail store goods with the evaluation focused on accurately recognizing and counting the number of such objects at checkout while accounting for clutter, and inter-object visual similarity and occlusion.

Important Dates

~~Data sets shared with participants: 2/27/2022~~
~~Evaluation server open to submissions: 03/15/2022~~
Challenge track submissions due: 04/09/2022 (11:59 PM, Pacific Time)
Evaluation submission is closed and rankings are finalized.
Workshop papers due: 04/13/2022 (11:59 PM, Pacific Time)
Since our review is not double-blind, papers should be submitted in final/camera-ready form.
Final papers due: Monday, April 18 (11:59 PM, Pacific Time)
All camera ready paper should be uploaded to CMT to be published by CVPR 2022. The accepted workshop papers will be accessible online at IEEE Xplore Digital Library and CVF Open Access.
Open source on GitHub (training code + testing code + additional annotation) due: 04/28/2022 (11:59 PM, Pacific Time)
All the competitors/candidates for awards MUST release their code for validation before decision of awardees. The performance on the leaderboard has to be reproducible without the use of external data.

ORGANIZING COMMITTEE

CITATIONS

Please cite the following papers accordingly if you choose to work with our datasets or refer to the previous challenge results:

2022 challenge summary paper – The 6th AI City Challenge

@InProceedings{Naphade22AIC22,
author = {M. Naphade and S. Wang and D. C. Anastasiu and Z. Tang and M. Chang and Y. Yao and L. Zheng and M. Shaiqur Rahman and A. Venkatachalapathy and A. Sharma and Q. Feng and V. Ablavsky and S. Sclaroff and P. Chakraborty and A. Li and S. Li and R. Chellappa},
title = {The 6th AI City Challenge},
booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
month = {June},
year = {2022},pages = {3346-3355},doi = {10.1109/CVPRW56347.2022.00378},publisher = {IEEE Computer Society}
}

2021 challenge summary paper – The 5th AI City Challenge

@InProceedings{Naphade21AIC21,
author = {Milind Naphade and Shuo Wang and David C. Anastasiu and Zheng Tang and Ming-Ching Chang and Xiaodong Yang and Yue Yao and Liang Zheng and Pranamesh Chakraborty and Christian E. Lopez and Anuj Sharma and Qi Feng and Vitaly Ablavsky and Stan Sclaroff},
title = {The 5th AI City Challenge},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2021}
}

2020 challenge summary paper – The 4th AI City Challenge

@InProceedings{Naphade20AIC20,
author = {Milind Naphade and Shuo Wang and David C. Anastasiu and Zheng Tang and Ming-Ching Chang and Xiaodong Yang and Liang Zheng and Anuj Sharma and Rama Chellappa and Pranamesh Chakraborty},

title = {The 4th AI City Challenge},

booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020},

pages = {2665–2674}

}

2019 challenge summary paper – The 2019 AI City Challenge

@InProceedings{Naphade19AIC19,
author = {Milind Naphade and Zheng Tang and Ming-Ching Chang and David C. Anastasiu and Anuj Sharma and Rama Chellappa and Shuo Wang and Pranamesh Chakraborty and Tingting Huang and Jenq-Neng Hwang and Siwei Lyu},
title = {The 2019 AI City Challenge},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019},
pages = {452–460}
}

2018 challenge summary paper – The 2018 AI City Challenge

@inproceedings{Naphade18AIC18,
author={Milind Naphade and Ming-Ching Chang and Anuj Sharma and David C. Anastasiu and Vamsi Jagarlamudi and Pranamesh Chakraborty and Tingting Huang and Shuo Wang and Ming-Yu Liu and Rama Chellappa and Jenq-Neng Hwang and Siwei Lyu},
title = {The 2018 NVIDIA AI City Challenge},
booktitle = {Proc. CVPR Workshops},
pages = {53-–60},
year = 2018
}

2017 challenge summary paper – The NVIDIA AI City Challenge

@inproceedings{Naphade17AIC17,

author={Milind Naphade and David C. Anastasiu and Anuj Sharma and Vamsi Jagrlamudi and Hyeran Jeon and Kaikai Liu and Ming-Ching Chang and Siwei Lyu and Zeyu Gao},

title={The NVIDIA AI City Challenge},

booktitle = {Prof. SmartWorld},

address = {Santa Clara, CA, USA},

year = 2017

}

Natural language-based vehicle retrieval dataset: CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions

@InProceedings{Feng21CityFlowNL,
author={Qi Feng and Vitaly Ablavsky and Stan Sclaroff},
title = {CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions},
howpublished = {arXiv:2101.04741},
year = {2021}
}

Vehicle MTMC tracking & re-identification dataset – CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

@InProceedings{Tang19CityFlow,
author = {Zheng Tang and Milind Naphade and Ming-Yu Liu and Xiaodong Yang and Stan Birchfield and Shuo Wang and Ratnesh Kumar and David Anastasiu and Jenq-Neng Hwang},

title = {CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019},

pages = {8797–8806}
}

Synthetic 3D vehicle dataset – Simulating Content Consistent Vehicle Datasets with Attribute Descent

@InProceedings{Yao20VehicleX,
author={Yue Yao and Liang Zheng and Xiaodong Yang and Milind Naphade and Tom Gedeon},

title = {Simulating Content Consistent Vehicle Datasets with Attribute Descent},
booktitle = {The European Conference on Computer Vision (ECCV)},

month = {August},
year = {2020},

pages = {775–791}
}