This repository contains our source code of Track 1 and Track 3 at the 2nd AI City Challenge Workshop in CVPR 2018. Our team won in both of the tracks at the challenge.
The source code of Track 1 is built in MATLAB and C++, with our trained YOLOv2 model provided.
The source code of Track 3 is developed in Python and C++, with our trained YOLOv2 model provided.
The code has been tested on Linux and Windows. Dependencies include CUDA, cuDNN and OpenCV.
The team members include Zheng (Thomas) Tang, Gaoang Wang, Hao (Alex) Xiao, and Aotian Zheng.
[Paper], [Slides], [Poster], [The 2nd AI City Challenge @ CVPR 2018]
The datasets for the 2nd AI City Challenge in CVPR 2018 are no longer available to the public. However, as the 3rd AI City Challenge Workshop was launched at CVPR 2019, they provided a new city-scale dataset for multi-camera vehicle tracking as well as image-based re-identification. They also had a new dataset for traffic anomaly detection. The scale of the datasets and the number of vehicles that are being used for evaluation are both unprecedented.
To access the new datasets, please follow the data access instructions at the AI City Challenge website. You may forward your inquiries to aicitychallenges@gmail.com.
The NVIDIA AI City Challenge Workshop at CVPR 2018 specifically focused on ITS problems such as
Our team participated in 2 out of 3 tracks:
Detailed information of this challenge can be found here.
Our team achieves rank #1 in both Track 1 and Track 3. The demo video for Track 1 can be viewed here. The demo video for Track 3 can be view here.
In SCT, the loss function in our data association algorithm consists of motion, temporal and appearance attributes. Especially, a histogram-based adaptive appearance model is designed to encode long-term appearance change. The change of loss is incorporated with a bottom-up clustering strategy for the association of tracklets. Robust 2D-to-3D projection is achieved with EDA optimization applied to camera calibration for speed estimation.
The proposed appearance model together with DCNN features, license plates, detected car types and traveling time information are combined for the computation of cost function in ICT.
Under the Track1 folder, there are 6 components:
Detailed description of each package is given in each subfolder.
Under the Track3 folder, there are 3 components:
Detailed description of each package is given in each subfolder.
The output of 1_Multi-Camera Vehicle Tracking and Re-identification is the similarity scores between pairs of vehicles for comparison. It can be converted into a distance score by inverse proportion. The output of 3_LP_COMP is the distance score between each two license plates. The final distance score between two vehicles is the multiplication of the above two distance scores.
Please consider to cite these papers in your publications if it helps your research:
@inproceedings{Tang18AIC,
author = {Zheng Tang and Gaoang Wang and Hao Xiao and Aotian Zheng and Jenq-Neng Hwang},
title = {Single-camera and inter-camera vehicle tracking and {3D} speed estimation based on fusion of visual and semantic features},
booktitle = {Proc. CVPR Workshops},
pages = {108--115},
year = {2018}
}
@misc{Tang17AIC,
author = {Zheng Tang and Gaoang Wang and Tao Liu and Young-Gun Lee and Adwin Jahn and Xu Liu and Xiaodong He and Jenq-Neng Hwang},
title = {Multiple-kernel based vehicle tracking using {3D} deformable model and camera self-calibration},
howpublished = {arXiv:1708.06831},
year = {2017}
}
For any question you can contact Zheng (Thomas) Tang.