pose2sim

Continuous integration PyPI version
Downloads Stars GitHub forks GitHub issues GitHub issues-closed
status DOI License

Pose2Sim

N.B:. Please set undistort_points and handle_LR_swap to false for now since it currently leads to inaccuracies. I’ll try to fix it soon.

News: Version 0.10.0:
OpenSim scaling and inverse kinematics are now integrated in Pose2Sim! No static trial needed.
Other recently added features: Pose estimation, Automatic camera synchronization, Multi-person analysis, Blender visualization, Marker augmentation, Batch processing. To upgrade, type pip install pose2sim --upgrade


Pose2Sim provides a workflow for 3D markerless kinematics, as an alternative to traditional marker-based MoCap methods.

Pose2Sim is free and open-source, low-cost but with research-grade accuracy and production-grade robustness. It gives a maximum of control on clearly explained parameters. Any combination of phones, webcams, or GoPros can be used with fully clothed subjects, so it is particularly adapted to the sports field, the doctor’s office, or for outdoor 3D animation capture.

Note: For real-time analysis with a single camera, please consider Sports2D (note that the motion must lie in the sagittal or frontal plane).


Fun fact:
Pose2Sim stands for “OpenPose to OpenSim”, as it originally used OpenPose inputs (2D keypoints coordinates) and lead to an OpenSim result (full-body 3D joint angles). Pose estimation is now performed with more recent models from RTMPose, and custom models (from DeepLabCut for example) can also be used.

</br>

Pose2Sim releases:

N.B.: As always, I am more than happy to welcome contributors (see How to contribute).

</br>

Contents

  1. Installation and Demonstration
    1. Installation
    2. Demonstration Part-1: End to end video to 3D joint angle computation
    3. Demonstration Part-2: Visualize your results with OpenSim or Blender
    4. Demonstration Part-3: Try multi-person analysis
    5. Demonstration Part-4: Try batch processing
  2. Use on your own data
    1. Setting up your project
    2. 2D pose estimation
      1. With RTMPose (default)
      2. With MMPose (coming soon)
      3. With DeepLabCut
      4. With OpenPose (legacy)
      5. With Mediapipe BlazePose (legacy)
      6. With AlphaPose (legacy)
    3. Camera calibration
      1. Convert from Qualisys, Optitrack, Vicon, OpenCap, EasyMocap, or bioCV
      2. Calculate from scratch
    4. Synchronizing, Associatiating, Triangulating, Filtering
      1. Synchronization
      2. Associate persons across cameras
      3. Triangulating keypoints
      4. Filtering 3D coordinates
      5. Marker augmentation
    5. OpenSim kinematics
      1. Within Pose2Sim
      2. Within OpenSim GUI
      3. Command Line
  3. Utilities
  4. How to cite and how to contribute
    1. How to cite
    2. How to contribute and to-do list

</br>

Installation and Demonstration

Installation

  1. Optional:
    Install Anaconda or Miniconda for simplicity and avoiding the risk of incompatibilities between libraries.

    Once installed, open an Anaconda prompt and create a virtual environment:

    conda create -n Pose2Sim python=3.9 -y 
conda activate Pose2Sim
  2. Install OpenSim:
    Install the OpenSim Python API (if you do not want to install via conda, refer to this page): 
    conda install -c opensim-org opensim -y
  3. Install Pose2Sim:
    If you don’t use Anaconda, type python -V in terminal to make sure python>=3.9 is installed.
    • OPTION 1: Quick install: Open a terminal. 
        pip install pose2sim
    • OPTION 2: Build from source and test the last changes: Open a terminal in the directory of your choice and Clone the Pose2Sim repository. 
        git clone --depth 1 https://github.com/perfanalytics/pose2sim.git
  cd pose2sim
  pip install .

  4. Optional:
    For faster inference, you can run on the GPU. Install pyTorch with CUDA and cuDNN support, and ONNX Runtime with GPU support (not available on MacOS).
    Be aware that GPU support takes an additional 6 GB on disk. The full installation is then 10.75 GB instead of 4.75 GB.

    Run nvidia-smi in a terminal. If this results in an error, your GPU is probably not compatible with CUDA. If not, note the “CUDA version”: it is the latest version your driver is compatible with (more information on this post).

    Then go to the ONNXruntime requirement page, note the latest compatible CUDA and cuDNN requirements. Next, go to the pyTorch website and install the latest version that satisfies these requirements (beware that torch 2.4 ships with cuDNN 9, while torch 2.3 installs cuDNN 8). For example:

    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124

    Finally, install ONNX Runtime with GPU support:

    pip install onnxruntime-gpu

    Check that everything went well within Python with these commands:

    import torch; import onnxruntime as ort
print(torch.cuda.is_available(), ort.get_available_providers())
# Should print "True ['CUDAExecutionProvider', ...]"

Note on storage use:
A full installation takes up to 11 GB of storage spate. However, GPU support is not mandatory and takes about 6 GB. Moreover, marker augmentation requires Tensorflow and does not necessarily yield better results. You can save an additional 1.3 GB by uninstalling it: pip uninstall tensorflow.
A minimal installation with carefully chosen pose models and without GPU support, Tensorflow, PyQt5 would take less than 3 GB.

</br>

Demonstration Part-1: End to end video to 3D joint angle computation

This demonstration provides an example experiment of a person balancing on a beam, filmed with 4 cameras.

Open a terminal, enter pip show pose2sim, report package location.
Copy this path and go to the Single participant Demo folder: cd <path>\Pose2Sim\Demo_SinglePerson.
Type ipython, and try the following code:

from Pose2Sim import Pose2Sim
Pose2Sim.calibration()
Pose2Sim.poseEstimation()
Pose2Sim.synchronization()
Pose2Sim.personAssociation()
Pose2Sim.triangulation()
Pose2Sim.filtering()
Pose2Sim.markerAugmentation()
Pose2Sim.kinematics()

3D marker locations are stored as .trc files in each trial folder in the pose-3d directory.
3D joint angles are stored as .mot files in the kinematics directory. Scaled models are also stored in the same directory.

</br>

Note:

</br>

Demonstration Part-2: Visualize your results with OpenSim or Blender

Visualize your results and look in detail for potential areas of improvement.

Basic visualization with the OpenSim GUI


Further check with the Pose2Sim Blender add-on


Demonstration Part-3: Try multi-person analysis

Another person, hidden all along, will appear when multi-person analysis is activated!

Go to the Multi-participant Demo folder: cd <path>\Pose2Sim\Demo_MultiPerson.
Type ipython, and try the following code:

from Pose2Sim import Pose2Sim
Pose2Sim.calibration()
Pose2Sim.poseEstimation()
# Pose2Sim.synchronization()
Pose2Sim.personAssociation()
Pose2Sim.triangulation()
Pose2Sim.filtering()
Pose2Sim.markerAugmentation()
Pose2Sim.kinematics()

or equivalently:

from Pose2Sim import Pose2Sim
Pose2Sim.runAll(do_synchronization=False) # Synchronization possible, but tricky with multiple persons

One .trc file per participant will be generated and stored in the pose-3d directory.
Similarly, one scaled .osim model and one joint angle .mot file per participant will be stored in the kinematicsfolder.

You can visualize your results with Blender as explained in Demonstration Part-2.


N.B.:


Demonstration Part-4: Try batch processing

Run numerous analysis with different parameters and minimal friction.

Go to the Batch Demo folder: cd <path>\Pose2Sim\Demo_Batch.
Type ipython, and try the following code:

from Pose2Sim import Pose2Sim
Pose2Sim.calibration()
Pose2Sim.poseEstimation()
Pose2Sim.synchronization()
Pose2Sim.personAssociation()
Pose2Sim.triangulation()
Pose2Sim.filtering()
Pose2Sim.markerAugmentation()
Pose2Sim.kinematics()

or equivalently:

from Pose2Sim import Pose2Sim
Pose2Sim.runAll()

The batch processing structure requires a Config.toml file in each of the trial directories. Global parameters are given in the Config.toml file of the BatchSession folder. They can be altered for specific Trials by uncommenting keys and their values in their respective Config.toml files.

Run Pose2Sim from the BatchSession folder if you want to batch process the whole session, or from a Trial folder if you want to process only a specific trial.

SingleTrial BatchSession
<pre>SingleTrial
├── calibration
├── videos
└── Config.toml</i></pre>		 <pre>BatchSession
├── calibration
├── Trial_1
│ ├── videos
│ └── Config.toml</i>
├── Trial_2
│ ├── videos
│ └── Config.toml</i>
└── Config.toml</i></pre>

For example, try uncommenting [project] and set frame_range = [10,99], or uncomment [pose] and set mode = 'lightweight' in the Config.toml file of Trial_2.

</br></br>

Use on your own data

N.B.: If a step is not relevant for your use case (synchronization, person association, marker augmentation…), you can just skip it.

Setting up your project

Get yourself comfy!

  1. Open a terminal, enter pip show pose2sim, report package location.
    Copy this path and do cd <path>\pose2sim.
  2. Copy-paste the Demo_SinglePerson, Demo_MultiPerson, or Demo_Batch folder wherever you like, and rename it as you wish.
  3. The rest of the tutorial will explain to you how to populate the Calibration and videos folders, edit the Config.toml files, and run each Pose2Sim step.

</br>

2D pose estimation

Estimate 2D pose from images with RTMPose or another pose estimation solution.

With RTMPose (default):

RTMPose is a state-of-the-art pose estimation solution that is faster and more accurate than OpenPose. It is now included in Pose2Sim for straightforward end-to-end analysis.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.poseEstimation()

</br>

N.B.: The GPU will be used with ONNX backend if a valid CUDA installation is found (or MPS with MacOS), otherwise the CPU will be used with OpenVINO backend.
N.B.: Pose estimation can be run in lightweight, balanced, or performance mode.
N.B.: Pose estimation can be dramatically sped up by increasing the value of det_frequency. In that case, the detection is only done every det_frequency frames, and bounding boxes are tracked inbetween (keypoint detection is still performed on all frames).
N.B.: Activating tracking will attempt to give consistent IDs to the same persons across frames, which might facilitate synchronization if other people are in the background.

</br>

With MMPose (coming soon):

Coming soon

</br>

With DeepLabCut:

If you need to detect specific points on a human being, an animal, or an object, you can also train your own model with DeepLabCut. In this case, Pose2Sim is used as an alternative to AniPose.

  1. Train your DeepLabCut model and run it on your images or videos (more instruction on their repository)
  2. Translate the h5 2D coordinates to json files (with DLC_to_OpenPose.py script, see Utilities). Note that the names of your camera folders must follow the same order as in the calibration file, and end with ‘_json’: 
    python -m DLC_to_OpenPose -i input_h5_file
  3. Edit pose.CUSTOM in Config.toml, and edit the node IDs so that they correspond to the column numbers of the 2D pose file, starting from zero. Make sure you also changed the pose_model and the tracked_keypoint.
    You can visualize your skeleton’s hierarchy by changing pose_model to CUSTOM and writing these lines: 
     config_path = r'path_to_Config.toml'
 import toml, anytree
 config = toml.load(config_path)
 pose_model = config.get('pose').get('pose_model')
 model = anytree.importer.DictImporter().import_(config.get('pose').get(pose_model))
 for pre, _, node in anytree.RenderTree(model): 
     print(f'{pre}{node.name} id={node.id}')
  4. Create an OpenSim model if you need inverse kinematics.

With OpenPose (legacy):

N.B.: RTMlib is faster, more accurate, and easier to install than OpenPose. This is a legacy option.
N.B.: OpenPose model files are apparently not available on their website anymore. Send me an email at dp2032@bath.ac.uk if you want me to forward them to you!

The accuracy and robustness of Pose2Sim have been thoroughly assessed only with OpenPose, BODY_25B model. Consequently, we recommend using this 2D pose estimation solution. See OpenPose repository for installation and running. Windows portable demo is enough.

With MediaPipe BlazePose (legacy):

N.B.: RTMlib is faster, more accurate, and easier to install than BlazePose. This is also a legacy option.

Mediapipe BlazePose is very fast, fully runs under Python, handles upside-down postures and wrist movements (but no subtalar ankle angles).
However, it is less robust and accurate than OpenPose, and can only detect a single person.

With AlphaPose (legacy):

N.B.: RTMlib is faster, more accurate, and easier to install than AlphaPose. This is also a legacy option.

AlphaPose is one of the main competitors of OpenPose, and its accuracy is comparable. As a top-down approach (unlike OpenPose which is bottom-up), it is faster on single-person detection, but slower on multi-person detection.
All AlphaPose models are supported (HALPE_26, HALPE_68, HALPE_136, COCO_133, COCO, MPII). For COCO and MPII, AlphaPose must be run with the flag “–format cmu”.

</br>

Camera calibration

Calculate camera intrinsic properties and extrinsic locations and positions.
Convert a preexisting calibration file, or calculate intrinsic and extrinsic parameters from scratch.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.calibration()

</br> Output file:

Convert from Qualisys, Optitrack, Vicon, OpenCap, EasyMocap, or bioCV

If you already have a calibration file, set calibration_type type to convert in your Config.toml file.

</br>

Calculate from scratch

Calculate calibration parameters with a checkerboard, with measurements on the scene, or automatically with detected keypoints.
Take heart, it is not that complicated once you get the hang of it!

N.B.: Try the calibration tool on the Demo by changing calibration_type to calculate in Config.toml.
For the sake of practicality, there are voluntarily few board images for intrinsic calibration, and few points to click for extrinsic calibration. In spite of this, your reprojection error should be under 1-2 cm, which does not hinder the quality of kinematic results in practice.).

</br>

Synchronizing, Associating, Triangulating, Filtering

Synchronization

Cameras need to be synchronized, so that 2D points correspond to the same position across cameras.
N.B.: Skip this step if your cameras are natively synchronized.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.synchronization()

</br>

For each camera, this computes mean vertical speed for the chosen keypoints, and finds the time offset for which their correlation is highest.
All keypoints can be taken into account, or a subset of them. The user can also specify a time for each camera when only one participant is in the scene, preferably performing a clear vertical motion.

N.B.: Works best when:

N.B.: Alternatively, synchronize cameras using a flashlight, a clap, or a clear event. GoPro cameras can also be synchronized with a timecode, by GPS (outdoors), or with their app (slightly less reliable).

</br>

Associate persons across cameras

If multi_person is set to false, the algorithm chooses the person for whom the reprojection error is smallest.
If multi_person is set to true, it associates across views the people for whom the distances between epipolar lines are the smallest. People are then associated across frames according to their displacement speed.

N.B.: Skip this step if only one person is in the field of view.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.personAssociation()

</br>

Check printed output. If results are not satisfying, try and release the constraints in the Config.toml file.

</br>

Triangulating keypoints

Triangulate your 2D coordinates in a robust way.
The triangulation is weighted by the likelihood of each detected 2D keypoint, provided that they this likelihood is above a threshold.
If the reprojection error is above another threshold, right and left sides are swapped; if it is still above, cameras are removed until the threshold is met. If more cameras are removed than a predefined number, triangulation is skipped for this point and this frame. In the end, missing values are interpolated.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.triangulation()

</br>

Check printed output, and visualize your trc in OpenSim: File -> Preview experimental data.
If your triangulation is not satisfying, try and release the constraints in the Config.toml file.

</br>

Filtering 3D coordinates

Filter your 3D coordinates.
Numerous filter types are provided, and can be tuned accordingly.

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.filtering()

</br>

Check your filtration with the displayed figures, and visualize your .trc file in OpenSim. If your filtering is not satisfying, try and change the parameters in the Config.toml file.

Output:

</br>

Marker Augmentation

Use the Stanford LSTM model to estimate the position of 47 virtual markers.
Note that inverse kinematic results are not necessarily better after marker augmentation. Skip if results are not convincing.

N.B.: Marker augmentation tends to give a more stable, but less precise output. In practice, it is mostly beneficial when using less than 4 cameras.

Make sure that participant_height is correct in your Config.toml file. participant_mass is mostly optional for IK.
Only works with models estimating at least the following keypoints (e.g., not COCO):

 ["Neck", "RShoulder", "LShoulder", "RHip", "LHip", "RKnee", "LKnee",
 "RAnkle", "LAnkle", "RHeel", "LHeel", "RSmallToe", "LSmallToe",
 "RBigToe", "LBigToe", "RElbow", "LElbow", "RWrist", "LWrist"]

Will not work properly if missing values are not interpolated (i.e., if there are Nan value in the .trc file).

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.markerAugmentation()

</br>

OpenSim kinematics

Obtain a scaled model and 3D joint angles.

This can be either done fully automatically within Pose2Sim, or manually within OpenSim GUI.

Within Pose2Sim

Scaling and inverse kinematics are performed in a fully automatic way for each trc file.
No need for a static trial!

Model scaling is done according to the mean of the segment lengths, across a subset of frames. We remove the 10% fastest frames (potential outliers), the frames where the speed is 0 (person probably out of frame), and the 40% most extreme segment values (potential outliers).

In your Config.toml file, set use_augmentation = false is you don’t want to use the results with augmented marker (this is sometimes better).
Set right_left_symmetry = false if you have good reasons to think the participant is not symmetrical (e.g. if they wear a prosthetic limb).

Open an Anaconda prompt or a terminal in a Session or Trial folder.
Type ipython.

from Pose2Sim import Pose2Sim
Pose2Sim.kinematics()

Once you have the scaled model and the joint angles, you are free to go further! Inverse dynamics, muscle analysis, etc. (make sure previously add muscles from the Pose2Sim model with muscles).


Within OpenSim GUI

If you are not fully satisfied with the results, you can perform scaling and inverse kinematics in a more traditional way, with (or without) a static trial.

Scaling

  1. Choose a time range where the 3D keypoints are particularly well reconstructed, or capture a static pose, typically an A-pose…
  2. Open OpenSim.
  3. File -> Open Model: Open the provided Model_Pose2Sim_LSTM.osim model from Pose2Sim/OpenSim_Setup.
    Note: Here and below, replace ‘LSTM’ by any other model if needed, e.g. HALPE_26
  4. Tools -> Scale model -> Load: Load the provided Scaling_Setup_Pose2Sim_LSTM.xml scaling file.
  5. Replace the example .trc file with your own data.
  6. Run
  7. File > Save Model: Save the new scaled OpenSim model.

Inverse kinematics

  1. Tools -> Inverse kinematics -> Load: Load the provided IK_Setup_Pose2Sim_LSTM.xml scaling file from Pose2Sim/OpenSim_Setup.
  2. Replace the example .trc file with your own data, and specify the path to your angle kinematics output file.
  3. Run.
  4. Right click on the Model->Motions->Coordinates > Save As: Save angle results

</br>

Command line

Alternatively, you can use command-line tools:

<!– - Take advantage of the full the OpenSim Python API. Run ipython:

See there for installation instructions (conda install may take a while). Make sure to replace py38np120 with your Python version (3.8 in this case) and with your numpy version (1.20 here).

  conda install -c opensim-org opensim-moco=4.4=py38np120 -y

If you run into a DLL error while importing opensim, open the file <Pose2Sim-env>\Lib\opensim\__init__.py and replace condaby conda-meta line 4. <Pose2Sim-env> location can be found with conda env list.\ –>

  import opensim
  opensim.ScaleTool("<PATH TO YOUR SCALING OR IK SETUP FILE>.xml").run()
  opensim.InverseKinematicsTool("<PATH TO YOUR SCALING OR IK SETUP FILE>.xml").run()

N.B.: You’ll need to adjust the time_range, output_motion_file, and enter the absolute path (NOT the relative path) to the input and output .osim, .trc, and .mot files in your setup file.

You can also run other API commands. See there for more instructions on how to use it.

</br>

Utilities

A list of standalone tools (see Utilities), which can be either run as scripts, or imported as functions. Check usage in the docstring of each Python file. The figure below shows how some of these tools can be used to further extend Pose2Sim usage.

Converting pose files (CLICK TO SHOW) 

[Blazepose_runsave.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/Blazepose_runsave.py)
Runs BlazePose on a video, and saves coordinates in OpenPose (json) or DeepLabCut (h5 or csv) format.

[DLC_to_OpenPose.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/DLC_to_OpenPose.py)
Converts a DeepLabCut (h5) 2D pose estimation file into OpenPose (json) files.

[AlphaPose_to_OpenPose.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/AlphaPose_to_OpenPose.py)
Converts AlphaPose single json file to OpenPose frame-by-frame files.
Converting calibration files (CLICK TO SHOW) 

[calib_toml_to_easymocap.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_toml_to_easymocap.py)
Converts an OpenCV .toml calibration file to EasyMocap intrinsic and extrinsic .yml calibration files.

[calib_easymocap_to_toml.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_easymocap_to_toml.py)
Converts EasyMocap intrinsic and extrinsic .yml calibration files to an OpenCV .toml calibration file.

[calib_from_checkerboard.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_from_checkerboard.py)
Calibrates cameras with images or a video of a checkerboard, saves calibration in a Pose2Sim .toml calibration file.
You should probably use Pose2Sim.calibration() instead, which is much easier and better.

[calib_qca_to_toml.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_qca_to_toml.py)
Converts a Qualisys .qca.txt calibration file to the Pose2Sim .toml calibration file (similar to what is used in [AniPose](https://anipose.readthedocs.io/en/latest/)).

[calib_toml_to_qca.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_toml_to_qca.py)
Converts a Pose2Sim .toml calibration file (e.g., from a checkerboard) to a Qualisys .qca.txt calibration file.

[calib_toml_to_opencap.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/calib_toml_to_opencap.py)
Converts an OpenCV .toml calibration file to OpenCap .pickle calibration files.

[calib_toml_to_opencap.py]( )
To convert OpenCap calibration tiles to a .toml file, please use Pose2Sim.calibration() and set convert_from = 'opencap' in Config.toml.
Plotting tools (CLICK TO SHOW) 

[json_display_with_img.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/json_display_with_img.py)
Overlays 2D detected json coordinates on original raw images. High confidence keypoints are green, low confidence ones are red.

[json_display_without_img.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/json_display_without_img.py)
Plots an animation of 2D detected json coordinates. 

[trc_plot.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_plot.py)
Displays X, Y, Z coordinates of each 3D keypoint of a TRC file in a different matplotlib tab.
Other trc tools (CLICK TO SHOW) 

[trc_from_easymocap.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_from_easymocap.py) 
Convert EasyMocap results keypoints3d .json files to .trc.

[c3d_to_trc.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/c3d_to_trc.py)
Converts 3D point data from a .c3d file to a .trc file compatible with OpenSim. No analog data (force plates, emg) nor computed data (angles, powers, etc.) are retrieved.

[trc_to_c3d.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_to_c3d.py)
Converts 3D point data from a .trc file to a .c3d file compatible with Visual3D.

[trc_desample.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_desample.py)
Undersamples a trc file.

[trc_Zup_to_Yup.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_Zup_to_Yup.py)
Changes Z-up system coordinates to Y-up system coordinates.

[trc_filter.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_filter.py)
Filters trc files. Available filters: Butterworth, Kalman, Butterworth on speed, Gaussian, LOESS, Median.

[trc_gaitevents.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_gaitevents.py)
Detects gait events from point coordinates according to [Zeni et al. (2008)](https://www.sciencedirect.com/science/article/abs/pii/S0966636207001804?via%3Dihub).

[trc_combine.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_combine.py)
Combine two trc files, for example a triangulated DeepLabCut trc file and a triangulated OpenPose trc file.

[trc_from_mot_osim.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/trc_from_mot_osim.py)
Build a trc file from a .mot motion file and a .osim model file.

[bodykin_from_mot_osim.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/bodykin_from_mot_osim.py)
Converts a mot file to a .csv file with rotation and orientation of all segments.

[reproj_from_trc_calib.py](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/Utilities/reproj_from_trc_calib.py)
Reprojects 3D coordinates of a trc file to the image planes defined by a calibration file. Output in OpenPose or DeepLabCut format.

</br>

How to cite and how to contribute

How to cite

If you use this code or data, please cite Pagnon et al., 2022b, Pagnon et al., 2022a, or Pagnon et al., 2021.

@Article{Pagnon_2022_JOSS, 
  AUTHOR = {Pagnon, David and Domalain, Mathieu and Reveret, Lionel}, 
  TITLE = {Pose2Sim: An open-source Python package for multiview markerless kinematics}, 
  JOURNAL = {Journal of Open Source Software}, 
  YEAR = {2022},
  DOI = {10.21105/joss.04362}, 
  URL = {https://joss.theoj.org/papers/10.21105/joss.04362}
 }

@Article{Pagnon_2022_Accuracy,
  AUTHOR = {Pagnon, David and Domalain, Mathieu and Reveret, Lionel},
  TITLE = {Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics—Part 2: Accuracy},
  JOURNAL = {Sensors},
  YEAR = {2022},
  DOI = {10.3390/s22072712},
  URL = {https://www.mdpi.com/1424-8220/22/7/2712}
}

@Article{Pagnon_2021_Robustness,
  AUTHOR = {Pagnon, David and Domalain, Mathieu and Reveret, Lionel},
  TITLE = {Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics—Part 1: Robustness},
  JOURNAL = {Sensors},
  YEAR = {2021},
  DOI = {10.3390/s21196530},
  URL = {https://www.mdpi.com/1424-8220/21/19/6530}
}

</br>

How to contribute and to-do list

I would happily welcome any proposal for new features, code improvement, and more!
If you want to contribute to Pose2Sim, please see this issue.
You will be proposed a to-do list, but please feel absolutely free to propose your own ideas and improvements.

</br>

Main to-do list

</br>

Detailed GOT-DONE and TO-DO list (CLICK TO SHOW) 
       
✔ **Pose:** Support OpenPose [body_25b](https://github.com/CMU-Perceptual-Computing-Lab/openpose_train/tree/master/experimental_models#body_25b-model---option-2-recommended) for more accuracy, [body_135](https://github.com/CMU-Perceptual-Computing-Lab/openpose_train/tree/master/experimental_models#single-network-whole-body-pose-estimation-model) for pronation/supination.
✔ **Pose:** Support [BlazePose](https://developers.google.com/mediapipe/solutions/vision/pose_landmarker) for faster inference (on mobile device).
✔ **Pose:** Support [DeepLabCut](http://www.mackenziemathislab.org/deeplabcut) for training on custom datasets.
✔ **Pose:** Support [AlphaPose](https://github.com/MVIG-SJTU/AlphaPose) as an alternative to OpenPose.
✔ **Pose:** Define custom model in config.toml rather than in skeletons.py.
✔ **Pose:** Integrate pose estimation within Pose2Sim (via RTMlib).
▢ **Pose:** Support [MMPose](https://github.com/open-mmlab/mmpose), [SLEAP](https://sleap.ai/), etc.
▢ **Pose:** Implement [RTMPoseW3D](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose3d) and monocular 3D kinematics
▢ **Pose:** Directly reading from DeepLabCut .csv or .h5 files instead of converting to .json (triangulation, person association, calibration, synchronization...) 
▢ **Pose:** GUI help for DeepLabCut model creation.

✔ **Calibration:** Convert [Qualisys](https://www.qualisys.com) .qca.txt calibration file.
✔ **Calibration:** Convert [Optitrack](https://optitrack.com/) extrinsic calibration file.
✔ **Calibration:** Convert [Vicon](http://www.vicon.com/Software/Nexus) .xcp calibration file.
✔ **Calibration:** Convert [OpenCap](https://www.opencap.ai/) .pickle calibration files.
✔ **Calibration:** Convert [EasyMocap](https://github.com/zju3dv/EasyMocap/) .yml calibration files.
✔ **Calibration:** Convert [bioCV](https://github.com/camera-mc-dev/.github/blob/main/profile/mocapPipe.md) calibration files.
✔ **Calibration:** Easier and clearer calibration procedure: separate intrinsic and extrinsic parameter calculation, edit corner detection if some are wrongly detected (or not visible). 
✔ **Calibration:** Possibility to evaluate extrinsic parameters from cues on scene.
▢ **Calibration:** Support vertical checkerboard.
▢ **Calibration:** Once object points have been detected or clicked once, track them for live calibration of moving cameras. Propose to click again when they are lost.
▢ **Calibration:** Calibrate cameras by pairs and compute average extrinsic calibration with [aniposelib](https://github.com/lambdaloop/aniposelib/blob/d03b485c4e178d7cff076e9fe1ac36837db49158/aniposelib/utils.py#L167). 
▢ **Calibration:** Fine-tune calibration with bundle adjustment.
▢ **Calibration:** Support ChArUco board detection (see [there](https://mecaruco2.readthedocs.io/en/latest/notebooks_rst/Aruco/sandbox/ludovic/aruco_calibration_rotation.html)).
▢ **Calibration:** Calculate calibration with points rather than board. (1) SBA calibration with wand (cf [Argus](https://argus.web.unc.edu), see converter [here](https://github.com/backyardbiomech/DLCconverterDLT/blob/master/DLTcameraPosition.py)). Set world reference frame in the end.
▢ **Calibration:** Alternatively, self-calibrate with [OpenPose keypoints](https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/cvi2.12130). Set world reference frame in the end.
▢ **Calibration:** Convert [fSpy calibration](https://fspy.io/) based on vanishing point.

✔ **Synchronization:** Synchronize cameras on keypoint speeds.
▢ **Synchronization:** Synchronize in multi-person mode: click on the person to synchronize on.

✔ **Person Association:** Automatically choose the main person to triangulate.
✔ **Person Association:** Multiple persons association. 1. Triangulate all the persons whose reprojection error is below a certain threshold (instead of only the one with minimum error), and then track in time with speed cf [Slembrouck 2020](https://link.springer.com/chapter/10.1007/978-3-030-40605-9_15)? or 2. Based on affinity matrices [Dong 2021](https://arxiv.org/pdf/1901.04111.pdf)? or 3. Based on occupancy maps [Yildiz 2012](https://link.springer.com/chapter/10.1007/978-3-642-35749-7_10)? or 4. With a neural network [Huang 2023](https://arxiv.org/pdf/2304.09471.pdf)?

✔ **Triangulation:** Triangulation weighted with confidence.
✔ **Triangulation:** Set a likelihood threshold below which a camera should not be used, a reprojection error threshold, and a minimum number of remaining cameras below which triangulation is skipped for this frame. 
✔ **Triangulation:** Interpolate missing frames (cubic, bezier, linear, slinear, quadratic)
✔ **Triangulation:** Show mean reprojection error in px and in mm for each keypoint.
✔ **Triangulation:** Show how many cameras on average had to be excluded for each keypoint.
✔ **Triangulation:** Evaluate which cameras were the least reliable.
✔ **Triangulation:** Show which frames had to be interpolated for each keypoint.
✔ **Triangulation:** Solve limb swapping (although not really an issue with Body_25b). Try triangulating with opposite side if reprojection error too large. Alternatively, ignore right and left sides, use RANSAC or SDS triangulation, and then choose right or left by majority voting. More confidence can be given to cameras whose plane is the most coplanar to the right/left line.
✔ **Triangulation:** [Undistort](https://docs.opencv.org/3.4/da/d54/group__imgproc__transform.html#ga887960ea1bde84784e7f1710a922b93c) 2D points before triangulating (and [distort](https://github.com/lambdaloop/aniposelib/blob/d03b485c4e178d7cff076e9fe1ac36837db49158/aniposelib/cameras.py#L301) them before computing reprojection error).
✔ **Triangulation:** Offer the possibility to augment the triangulated data with [the OpenCap LSTM](https://github.com/stanfordnmbl/opencap-core/blob/main/utilsAugmenter.py). Create "BODY_25_AUGMENTED" model, Scaling_setup, IK_Setup. 
✔ **Triangulation:** Multiple person kinematics (output multiple .trc coordinates files). Triangulate all persons with reprojection error above threshold, and identify them by minimizing their displacement across frames.
▢ **Triangulation:** Pre-compile weighted_triangulation and reprojection with @jit(nopython=True, parallel=True) for faster execution.
▢ **Triangulation:** Offer the possibility of triangulating with Sparse Bundle Adjustment (SBA), Extended Kalman Filter (EKF), Full Trajectory Estimation (FTE) (see [AcinoSet](https://github.com/African-Robotics-Unit/AcinoSet)).
▢ **Triangulation:** Implement normalized DLT and RANSAC triangulation, Outlier rejection (sliding z-score?), as well as a [triangulation refinement step](https://doi.org/10.1109/TMM.2022.3171102).
▢ **Triangulation:** Track hands and face (won't be taken into account in OpenSim at this stage).

✔ **Filtering:** Available filtering methods: Butterworth, Butterworth on speed, Gaussian, Median, LOESS (polynomial smoothing).
✔ **Filtering:** Implement Kalman filter and Kalman smoother.
▢ **Filtering:** Implement [smoothNet](https://github.com/perfanalytics/pose2sim/issues/29)

✔ **OpenSim:** Integrate better spine from [lifting fullbody model](https://pubmed.ncbi.nlm.nih.gov/30714401) to the [gait full-body model](https://nmbl.stanford.edu/wp-content/uploads/07505900.pdf), more accurate for the knee.
✔ **OpenSim:** Optimize model marker positions as compared to ground-truth marker-based positions.
✔ **OpenSim:** Add scaling and inverse kinematics setup files.
✔ **OpenSim:** Add full model with contact spheres ([SmoothSphereHalfSpaceForce](https://simtk.org/api_docs/opensim/api_docs/classOpenSim_1_1SmoothSphereHalfSpaceForce.html#details)) and full-body muscles ([DeGrooteFregly2016Muscle](https://simtk.org/api_docs/opensim/api_docs/classOpenSim_1_1DeGrooteFregly2016Muscle.html#details)), for [Moco](https://opensim-org.github.io/opensim-moco-site/) for example.
✔ **OpenSim:** Add model with [ISB shoulder](https://github.com/stanfordnmbl/opencap-core/blob/main/opensimPipeline/Models/LaiUhlrich2022_shoulder.osim).
✔ **OpenSim:** Integrate OpenSim in Pose2Sim.
▢ **OpenSim:** Do not require a separate scaling trial: scale on the 10% slowest frames of the moving trial instead, or take median scaling value.
▢ **OpenSim:** Implement optimal fixed-interval Kalman smoothing for inverse kinematics ([this OpenSim fork](https://github.com/antoinefalisse/opensim-core/blob/kalman_smoother/OpenSim/Tools/InverseKinematicsKSTool.cpp)), or [Biorbd](https://github.com/pyomeca/biorbd/blob/f776fe02e1472aebe94a5c89f0309360b52e2cbc/src/RigidBody/KalmanReconsMarkers.cpp))

✔ **GUI:** Blender add-on (cf [MPP2SOS](https://blendermarket.com/products/mocap-mpp2soss)), [Maya-Mocap](https://github.com/davidpagnon/Maya-Mocap) and [BlendOsim](https://github.com/JonathanCamargo/BlendOsim).
▢ **GUI:** App or webapp (e.g., with [gradio](https://www.gradio.app/playground), [Streamlit](https://streamlit.io/), or [Napari](https://napari.org/stable) ). Also see [tkinter](https://realpython.com/python-gui-tkinter) interfaces (or [Kivy](https://kivy.org/) if we want something nice and portable, or [Google Colab](https://colab.research.google.com/)). Maybe have a look at the [Deeplabcut GUI](https://github.com/DeepLabCut/DeepLabCut/) for inspiration.
▢ **GUI:** 3D plot of cameras and of triangulated keypoints.
▢ **GUI:** Demo on Google Colab (see [Sports2D](https://bit.ly/Sports2D_Colab) for OpenPose and Python package installation on Google Drive).

✔ **Demo:** Provide Demo data for users to test the code.
✔ **Demo:** Add videos for users to experiment with other pose detection frameworks
✔ **Demo:** Time shift videos and json to demonstrate synchronization
✔ **Demo:** Add another virtual person to demonstrate personAssociation
▢ **Tutorials:** Make video tutorials.
▢ **Doc:** Use [Sphinx](https://www.sphinx-doc.org/en/master), [MkDocs](https://www.mkdocs.org), or [github.io](https://docs.github.com/fr/pages/quickstart) (maybe better) for clearer documentation.

✔ **Pip package**
✔ **Batch processing** (also enable non-batch processing)
✔ **Catch errors**
▢ **Conda package** 
▢ **Docker image**
▢  Integrate [Sports2D](https://github.com/davidpagnon/Sports2D/) for OpenSim analysis from a single camera
▢ Real-time: Run Pose estimation, Person association, Triangulation, Kalman filter, IK frame by frame (instead of running each step for all frames)
▢ Config parameter for non batch peocessing

▢ **Run from command line via click or typer**
▢ **Utilities**: Export other data from c3d files into .mot or .sto files (angles, powers, forces, moments, GRF, EMG...)
▢ **Utilities**: Create trc_to_c3d.py script

✔ **Bug:** calibration.py. FFMPEG error message when calibration files are images. See [there](https://github.com/perfanalytics/pose2sim/issues/33#:~:text=In%20order%20to%20check,filter%20this%20message%20yet.).
✔ **Bug:** common.py, class plotWindow(). Python crashes after a few runs of `Pose2Sim.filtering()` when `display_figures=true`. See [there](https://github.com/superjax/plotWindow/issues/7).

</br>

Acknowledgements:

This site is open source. Improve this page.