MaochengHu 576cda45b8 first commit		2 years ago
..
cpp	576cda45b8 first commit	2 years ago
python	576cda45b8 first commit	2 years ago
README.md	576cda45b8 first commit	2 years ago
README_cn.md	576cda45b8 first commit	2 years ago
README_en.md	576cda45b8 first commit	2 years ago

English | 简体中文

Real-time Multi-Object Tracking system PP-Tracking

PP-Tracking is the first open source real-time Multi-Object Tracking system, and it is based on PaddlePaddle deep learning framework. It has rich models, wide application and high efficiency deployment.

PP-Tracking supports two paradigms: single camera tracking (MOT) and multi-camera tracking (MTMCT). Aiming at the difficulties and pain points of actual business, PP-Tracking provides various MOT functions and applications such as pedestrian tracking, vehicle tracking, multi-class tracking, small object tracking, traffic statistics and multi-camera tracking. The deployment method supports API and GUI visual interface, and the deployment language supports Python and C++, The deployment platform environment supports Linux, NVIDIA Jetson, etc.

video source：VisDrone and BDD100K dataset

一、Quick Start

AI studio public project case

PP-tracking provides AI studio public project cases. Please refer to this tutorial.

Python predict and deployment

PP-Tracking supports Python predict and deployment. Please refer to this doc.

C++ predict and deployment

PP-Tracking supports C++ predict and deployment. Please refer to this doc.

GUI predict and deployment

PP-Tracking supports GUI predict and deployment. Please refer to this doc.

二、Model Zoo

PP-Tracking supports two paradigms: single camera tracking (MOT) and multi-camera tracking (MTMCT).

Single camera tracking supports FairMOT and DeepSORT two MOT models, multi-camera tracking only support DeepSORT.
The applications of single camera tracking include pedestrian tracking, vehicle tracking, multi-class tracking, small object tracking and traffic statistics. The models are mainly optimized based on FairMOT to achieve the effect of real-time tracking. At the same time, PP-Tracking provides pre-training models based on different application scenarios.
In DeepSORT (including DeepSORT used in multi-camera tracking), the selected detectors are PaddeDetection's self-developed high-performance detector PP-YOLOv2 and lightweight detector PP-PicoDet, and the selected ReID model is PaddleClas's self-developed ultra lightweight backbone PP-LCNet

PP-Tracking provids multi-scenario pre-training models and the exported models for deployment:

Scene	Dataset	MOTA	Speed（FPS）	config	model weights	inference model
pedestrian	MOT17	65.3	23.9	config	download	download
pedestrian(small objects)	VisDrone-pedestrian	40.5	8.35	config	download	download
vehicle	BDD100k-vehicle	32.6	24.3	config	download	download
vehicle(small objects)	VisDrone-vehicle	39.8	22.8	config	download	download
multi-class	BDD100k	-	12.5	config	download	download
multi-class(small objects)	VisDrone	20.4	6.74	config	download	download

Note：

The equipment predicted by the model is NVIDIA Jetson Xavier NX, the speed is tested by TensorRT FP16, and the test environment is CUDA 10.2, JETPACK 4.5.1, TensorRT 7.1.
model weights means the weights saved directly after PaddleDetection training. For more tracking model weights, please refer to modelzoo, you can also train according to the corresponding model config file and get the model weights.
inference model means the model weights with only forward parameters after exported, because only forward parameters are required during the deployment of PP-Tracking project. It can be downloaded and exported according to modelzoo, you can also train according to the corresponding model config file and get the model weights, and then export them。In exported model files, there should be infer_cfg.yml,model.pdiparams,model.pdiparams.info and model.pdmodel four files in total, which are generally packaged in tar format.

Citations

@ARTICLE{9573394,
  author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title={Detection and Tracking Meet Drones Challenge},
  year={2021},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TPAMI.2021.3119563}
}
@InProceedings{bdd100k,
    author = {Yu, Fisher and Chen, Haofeng and Wang, Xin and Xian, Wenqi and Chen,
              Yingying and Liu, Fangchen and Madhavan, Vashisht and Darrell, Trevor},
    title = {BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning},
    booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2020}
}
@article{zhang2020fair,
  title={FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking},
  author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
  journal={arXiv preprint arXiv:2004.01888},
  year={2020}
}
@inproceedings{Wojke2018deep,
  title={Deep Cosine Metric Learning for Person Re-identification},
  author={Wojke, Nicolai and Bewley, Alex},
  booktitle={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2018},
  pages={748--756},
  organization={IEEE},
  doi={10.1109/WACV.2018.00087}
}

README.md