RapidPoseTriangulation

Fast triangulation of multiple persons from multiple camera views.
A general overview can be found in the paper RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond.

     

Build

• Clone this project with submodules:

  git clone --recurse-submodules https://gitlab.com/Percipiote/RapidPoseTriangulation.git
  cd RapidPoseTriangulation/
  

• Enable GPU-access for docker building:

  • Install nvidia container tools: Link

  • Run sudo nano /etc/docker/daemon.json and add:

    {
      "runtimes": {
        "nvidia": {
          "args": [],
          "path": "nvidia-container-runtime"
        }
      },
      "default-runtime": "nvidia"
    }
    

  • Restart docker: sudo systemctl restart docker

• Build docker container:

  docker build --progress=plain -t rapidposetriangulation .
  ./run_container.sh
  

• Build triangulator:

  cd /RapidPoseTriangulation/swig/ && make all && cd ../tests/ && python3 test_interface.py && cd ..
  
  cd /RapidPoseTriangulation/scripts/ && \
  g++ -std=c++2a -fPIC -O3 -march=native -Wall -Werror -flto=auto \
    -I /RapidPoseTriangulation/rpt/ \
    -isystem /usr/include/opencv4/ \
    -isystem /onnxruntime/include/ \
    -isystem /onnxruntime/include/onnxruntime/core/session/ \
    -isystem /onnxruntime/include/onnxruntime/core/providers/tensorrt/ \
    -L /onnxruntime/build/Linux/Release/ \
    test_skelda_dataset.cpp \
    /RapidPoseTriangulation/rpt/*.cpp \
    -o test_skelda_dataset.bin \
    -Wl,--start-group \
      -lonnxruntime_providers_tensorrt \
      -lonnxruntime_providers_shared \
      -lonnxruntime_providers_cuda \
      -lonnxruntime \
    -Wl,--end-group \
    $(pkg-config --libs opencv4) \
    -Wl,-rpath,/onnxruntime/build/Linux/Release/ \
  && cd ..
  

• Download ONNX models from model registry and save them to mmdeploy/extras/exports/. Upon the first usage, they will be converted to TensorRT models, which will take a few minutes.
  (Note that this conversion is not deterministic and will each time result in slightly different models and therefore also slightly different benchmark results.)

• Test with samples:

  python3 /RapidPoseTriangulation/scripts/test_triangulate.py
  

• Test with skelda dataset:

  export CUDA_VISIBLE_DEVICES=0
  python3 /RapidPoseTriangulation/scripts/test_skelda_dataset.py
  

Extras

• Exporting tools for 2D models are at mmdeploy directory.

• For usage in combination with ROS2 see ros directory.

• Running on a Nvidia Jetson is also possible following jetson directory.

Citation

Please cite RapidPoseTriangulation if you found it helpful for your research or business.

@article{
  rapidtriang,
  title={{RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond}},
  author={Bermuth, Daniel and Poeppel, Alexander and Reif, Wolfgang},
  journal={arXiv preprint arXiv:2503.21692},
  year={2025}
}