oclreid

[video input] Person Re-Identification for Robot Person Following with Online Continual Learning

https://github.com/medlartea/oclreid

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

[video input] Person Re-Identification for Robot Person Following with Online Continual Learning

Basic Info
  • Host: GitHub
  • Owner: MedlarTea
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 217 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

OCLReID

This project is for target person tracking based on mmtrack framework. For running this code with robot/rosbag, please refer to OCL-RPF

Install

For Video Running Only

Create a conda environment and install OCLReID (based on mmtrack), worked in RTX3090 ```bash git clone https://github.com/MedlarTea/OCLReID cd OCLReID conda create -n oclreid python=3.7 conda activate oclreid conda install pytorch=1.11 cudatoolkit=11.3 torchvision=0.12.0 -c pytorch pip install mmcv-full==1.5.3 -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.11.0/index.html pip install mmdet==2.26.0 pip install -r requirements.txt pip install -r requirements/build.txt pip install -v -e .

install orientation estimation method

cd mmtrack/models/orientation pip install -r requirements.txt pip install -v -e . ```

Download pre-trained weights for OCLReID - Download 2d joint detection models: Google drive and put the checkpoints to OCLReID/mmtrack/models/pose/Models/sppe. - Download ReID models: Google drive, then make directory OCLReID/checkpoints/reid and put the checkpoints to it.

Run It!

Video Running

bash cd OCLReID python run_video.py --show_result This would run the ./demo.mp4.

Run on the customized dataset

Our customized dataset is provided in dataset directory with four scenarios: corridor1, corridor2, lab_corridor and room. We provide raw_video.mp4 and labels.txt for each scenario. Specifically, bbox annotations in the label.txt are represented as x1,y1,w,h.

Note: the annotations are rough, but should be enough for evaluating the ReID performance of algorithms.

Citation

@article{ye2024oclrpf, title={Person re-identification for robot person following with online continual learning}, author={Ye, Hanjing and Zhao, Jieting and Zhan, Yu and Chen, Weinan and He, Li and Zhang, Hong}, journal={IEEE Robotics and Automation Letters}, year={2024}, publisher={IEEE} }

Owner

  • Name: MedlarTea
  • Login: MedlarTea
  • Kind: user

GitHub Events

Total
  • Watch event: 6
  • Push event: 8
  • Fork event: 2
  • Create event: 2
Last Year
  • Watch event: 6
  • Push event: 8
  • Fork event: 2
  • Create event: 2

Dependencies

docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
mmtrack/models/pose/YOLOX/demo/ncnn/android/app/build.gradle maven
mmtrack/models/pose/YOLOX/demo/ncnn/android/build.gradle maven
mmtrack/models/orientation/requirements.txt pypi
  • Cython *
  • EasyDict *
  • json_tricks *
  • opencv-python *
  • pandas *
  • pyyaml *
  • scikit-image *
  • scipy *
  • shapely *
  • tensorboardX *
  • yacs >=0.1.5
mmtrack/models/orientation/setup.py pypi
  • matplotlib >=3.0
  • numpy >=1.15
mmtrack/models/pose/YOLOX/requirements.txt pypi
  • Pillow *
  • loguru *
  • ninja *
  • numpy *
  • onnx ==1.8.1
  • onnx-simplifier ==0.3.5
  • onnxruntime ==1.8.0
  • opencv_python *
  • scikit-image *
  • tabulate *
  • tensorboard *
  • thop *
  • torch >=1.7
  • torchvision *
  • tqdm *
mmtrack/models/pose/YOLOX/setup.py pypi
requirements/build.txt pypi
  • cython *
  • numba ==0.53.0
  • numpy *
requirements/debug.txt pypi
  • fitlog *
  • imageio *
  • visdom *
requirements/docs.txt pypi
  • myst_parser *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
requirements/mminstall.txt pypi
  • mmcls >=0.16.0
  • mmcv-full >=1.3.17,<1.6.0
  • mmdet >=2.19.1,<3.0.0
requirements/readthedocs.txt pypi
  • mmcls *
  • mmcv *
  • mmdet *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • attributee ==0.1.5
  • dotty_dict *
  • lap *
  • matplotlib *
  • mmcls >=0.16.0
  • motmetrics *
  • packaging *
  • pandas <=1.3.5
  • pycocotools <=2.0.2
  • scipy <=1.7.3
  • seaborn *
  • terminaltables *
  • tqdm *
requirements/tests.txt pypi
  • asynctest * test
  • codecov * test
  • flake8 * test
  • interrogate * test
  • isort ==4.3.21 test
  • kwarray * test
  • pytest * test
  • ubelt * test
  • xdoctest >=0.10.0 test
  • yapf * test
requirements.txt pypi
  • Pillow >=7.1.2
  • PyYAML >=5.3.1
  • catkin_pkg *
  • defusedxml *
  • easydict *
  • fitlog *
  • imageio *
  • loguru ==0.5.3
  • matplotlib >=3.2.2
  • numpy >=1.18.5
  • opencv-python >=4.1.2
  • pandas >=1.1.4
  • pycocotools ==2.0.0
  • requests >=2.23.0
  • rosnumpy *
  • rospkg *
  • scikit-learn *
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • sympy *
  • tabulate ==0.8.9
  • thop ==0.0.31.post2005241907
  • torch >=1.7.0
  • torchmetrics *
  • torchvision >=0.8.1
  • tqdm >=4.41.0
  • visdom *
setup.py pypi