fulyvv/pose2sim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/perfanalytics/pose2sim

Browse Source
This commit is contained in:
davidpagnon 2024-05-13 11:27:56 +02:00
commit f474838ff8
2 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -73,7 +73,7 @@ If you can only use one single camera and don't mind losing some accuracy, pleas
4. [Camera calibration](#camera-calibration)
1. [Convert from Qualisys, Optitrack, Vicon, OpenCap, EasyMocap, or bioCV](#convert-from-qualisys-optitrack-vicon-opencap-easymocap-or-biocv)
2. [Calculate from scratch](#calculate-from-scratch)
5. [Synchronization, Tracking, Triangulating, Filtering](#synchronization-tracking-triangulating-filtering)
5. [Synchronizing, Tracking, Triangulating, Filtering](#synchronizing-tracking-triangulating-filtering)
1. [Synchronization](#synchronization)
2. [Associate persons across cameras](#associate-persons-across-cameras)
3. [Triangulating keypoints](#triangulating-keypoints)
@ -96,7 +96,7 @@ If you can only use one single camera and don't mind losing some accuracy, pleas
1. **Install OpenPose** (instructions [there](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/installation/0_index.md)). \
*Windows portable demo is enough.*
2. **Install OpenSim 4.x** ([there](https://simtk.org/frs/index.php?group_id=91)). \
*Tested up to v4.4-beta on Windows. Has to be compiled from source on Linux (see [there](https://simtk-confluence.stanford.edu:8443/display/OpenSim/Linux+Support)).*
*Tested up to v4.5 on Windows. Has to be compiled from source on Linux (see [there](https://simtk-confluence.stanford.edu:8443/display/OpenSim/Linux+Support)).*
3. ***Optional.*** *Install Anaconda or [Miniconda](https://docs.conda.io/en/latest/miniconda.html). \
Open an Anaconda terminal and create a virtual environment with typing:*
<pre><i>conda create -n Pose2Sim python=3.8 -y
@ -136,8 +136,11 @@ Pose2Sim.markerAugmentation()
```
3D results are stored as .trc files in each trial folder in the `pose-3d` directory.
*N.B.:* Default parameters have been provided in [Config.toml](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/S01_Demo_SingleTrial/Config.toml) but can be edited.\
*N.B.:* *Try the calibration tool by changing `calibration_type` to `calculate` instead of `convert` (more info [there](#calculate-from-scratch)).*
*N.B.:* Default parameters have been provided in [Config.toml](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/S01_Demo_SingleTrial/Config.toml) but can be edited.
</br>
__*Go further:*__ Try the calibration tool by changing `calibration_type` to `calculate` instead of `convert` in [Config.toml](https://github.com/perfanalytics/pose2sim/blob/main/Pose2Sim/S01_Demo_SingleTrial/Config.toml) (more info [there](#calculate-from-scratch)).
<br/>
@ -153,7 +156,7 @@ Pose2Sim.markerAugmentation()
### Inverse kinematics
1. Load the provided `IK_Setup_Pose2Sim_LSTM.xml` scaling file from `Pose2Sim/OpenSim_Setup`. *(Tools -> Inverse kinematics -> Load)*
2. Run. You should see your skeletal model move in the Vizualizer window.
2. Run. You should see your skeletal model move in the Visualizer window.
5. Your IK motion file will be saved in `S00_P00_OpenSim`.
<br/>
@ -792,7 +795,6 @@ You will be proposed a to-do list, but please feel absolutely free to propose yo
&#10004; **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).
&#10004; **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.
&#10004; **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.
&#9634; **Triangulation:** If the gap is larger than the interpolation threshold, fill it with previous frames instead of leaving it blank.
&#9634; **Triangulation:** Pre-compile weighted_triangulation and reprojection with @jit(nopython=True, parallel=True) for faster execution.
&#9634; **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)).
&#9634; **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).

2
setup.cfg
View File

@ -1,6 +1,6 @@
[metadata]
name = pose2sim
version = 0.8.1
version = 0.8.3
author = David Pagnon
author_email = contact@david-pagnon.com
description = Perform a markerless kinematic analysis from multiple calibrated views as a unified workflow from an OpenPose input to an OpenSim result.