Repository files navigation

PySOT is a software system designed by SenseTime Video Intelligence Research team. It implements state-of-the-art single object tracking algorithms, includingSiamRPN andSiamMask. It is written in Python and powered by thePyTorch deep learning framework. This project also contains a Python port of toolkit for evaluating trackers.

PySOT has enabled research projects, including: SiamRPN, DaSiamRPN, SiamRPN++, and SiamMask.

Example SiamFC, SiamRPN and SiamMask outputs.

The goal of PySOT is to provide a high-quality, high-performance codebase for visual trackingresearch. It is designed to be flexible in order to support rapid implementation and evaluation of novel research. PySOT includes implementations of the following visual tracking algorithms:

• SiamMask
• SiamRPN++
• DaSiamRPN
• SiamRPN
• SiamFC

using the following backbone network architectures:

• ResNet{18, 34, 50}
• MobileNetV2
• AlexNet

Additional backbone architectures may be easily implemented. For more details about these models, please seeReferences below.

Evaluation toolkit can support the following datasets:

📎OTB2015📎VOT16/18/19📎VOT18-LT📎LaSOT📎UAV123

We provide a large set of baseline results and trained models available for download in thePySOT Model Zoo.

Please find installation instructions for PyTorch and PySOT inINSTALL.md.

export PYTHONPATH=/path/to/pysot:$PYTHONPATH

Download models inPySOT Model Zoo and put the model.pth in the correct directory in experiments

python tools/demo.py \    --config experiments/siamrpn_r50_l234_dwxcorr/config.yaml \    --snapshot experiments/siamrpn_r50_l234_dwxcorr/model.pth# --video demo/bag.avi # (in case you don't have webcam)

Download datasets and put them intotesting_dataset directory. Jsons of commonly used datasets can be downloaded fromGoogle Drive orBaiduYun. If you want to test tracker on new dataset, please refer topysot-toolkit to settingtesting_dataset.

cd experiments/siamrpn_r50_l234_dwxcorrpython -u ../../tools/test.py \--snapshot model.pth\# model path--dataset VOT2018\# dataset name--config config.yaml# config file

The testing results will in the current directory(results/dataset/model_name/)

assume still in experiments/siamrpn_r50_l234_dwxcorr_8gpu

python ../../tools/eval.py  \--tracker_path ./results\# result path--dataset VOT2018\# dataset name--num 1\# number thread to eval--tracker_prefix'model'# tracker_name

SeeTRAIN.md for detailed instruction.

If you meet problem, try searching our GitHub issues first. We intend the issues page to be a forum in which the community collectively troubleshoots problems. But please donot postduplicate issues. If you have similar issue that has been closed, you can reopen it.

• ModuleNotFoundError: No module named 'pysot'

🎯Solution: Runexport PYTHONPATH=path/to/pysot first before you run the code.

• ImportError: cannot import name region

🎯Solution: Buildregion bypython setup.py build_ext —-inplace as decribled inINSTALL.md.

• Fast Online Object Tracking and Segmentation: A Unifying Approach.Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H.S. Torr.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

• SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks.Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

• Distractor-aware Siamese Networks for Visual Object Tracking.Zheng Zhu, Qiang Wang, Bo Li, Wu Wei, Junjie Yan, Weiming Hu.The European Conference on Computer Vision (ECCV), 2018.

• High Performance Visual Tracking with Siamese Region Proposal Network.Bo Li, Wei Wu, Zheng Zhu, Junjie Yan, Xiaolin Hu.IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

• Fully-Convolutional Siamese Networks for Object Tracking.Luca Bertinetto, Jack Valmadre, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr.The European Conference on Computer Vision (ECCV) Workshops, 2016.

• Fangyi Zhang
• Qiang Wang
• Bo Li
• Zhiyuan Chen
• Jinghao Zhou

PySOT is released under theApache 2.0 license.