-
Notifications
You must be signed in to change notification settings - Fork 3
Home
20.4.2020: No need to install btk separately anymore - everything should just work, as long as you install on a 64-bit version of Python 2.7.
Gaitutils can be used to extract, process and visualize gait data (raw data, model outputs, EMG data). It supports reading data from Vicon Nexus or directly from c3d files. Note that it is still under heavy development.
This is a 'quick start' guide to help with installation and use of the graphical interface. The Python API is not comprehensively documented but may be in the future, especially if I get requests for that.
Anaconda is the recommended distribution. Alternatively you can use Miniconda for a smaller download. The Python version (2.7 or 3.x) does not matter, since the correct Python version is automatically installed via the environment (see below). However using a reasonably recent Anaconda version is a good idea. Also, the installation is easiest if you use a 64-bit Python environment (amd64). Currently, a Python 2.7 environment will be installed for gaitutils, mostly because Vicon Nexus still supports Python 2 only.
Conda supports a feature called environments. Each enviroment can have its own Python version and a set of packages.
Gaitutils comes with a conda enviroment file that allows you to conveniently install all required packages into an environment. If you want to install the packages manually, see the Appendix instead.
Open Anaconda Prompt from Windows menu. Download the environment specification by giving the command:
curl -O http://raw.githubusercontent.com/jjnurminen/gaitutils/master/environment.yml
Alternatively, if curl does not work, download environment.yml by visiting the link given in the above command and saving the file. Make sure that it is saved under the correct filename - the browser save dialog may change the name. Then create the environment by typing:
conda env create -f environment.yml
To activate the environment in Anaconda Prompt, type
conda activate gaitutils
This will activate the environment for the current session only. For instructions on how to activate it every time you open the shell, see the Appendix. However, you may not need to use the shell
After activating the environment, you can run
gaitmenu
to start the graphical user interface to gaitutils.
In the activated environment, type
gaitmenu_make_shortcut
An icon should appear on your desktop, which will start the menu in the correct environment.
The graphical interface allows plotting of trials from running Vicon Nexus instance. You can plot either the current trial or 'tagged' trials from the current session. Tags refer to specific strings in the Eclipse database. By default, the tags are searched for in Eclipse 'Notes' and 'Description' fields (this can be configured). The default tags are E1, E2, E3, E4, T1, T2, T3, T4. You can change the tags in the config (see below).
The layout defines the variables to plot. Some common layouts such as Plug-in Gait come predefined with the software. You can also define your own layouts.
Two different plotting backends are currently supported: plotly and matplotlib. The Plotly backend creates interactive plots in a web browser. The matplotlib package creates static plots that may be more useful for hardcopies.
The autoprocessing functionality is intended for processing of dynamic trials in gait sessions (may also work for running, but less tested). It works in conjunction with Vicon Nexus and performs the following tasks:
- run preprocessing pipeline(s)
- evaluate forceplate contact for each forceplate and mark the corresponding Eclipse database fields
- mark gait events (foot strike and toeoff)
- run dynamic model(s)
- write trial info (processing results) into Eclipse, e.g. Description or Notes field
You should first create two pipelines in Nexus, called "Preprocessing" and "Dynamic model". The first should yield filtered marker trajectories, i.e. it should perform reconstruct, label gap fill (if necessary) and filter operations. You may also want to filter analog (forceplate) data. The "Dynamic model" pipeline should run any subsequent modelling operations, e.g. Plug-in Gait. Save operations are not needed in either pipeline.
NOTE: it has been found out that long pipelines with multiple operations may cause Nexus to occasionally crash. If you experience this, break your preprocessing pipeline into a set of several smaller pipelines and specify those in the gaitutils configuration instead (see Options/Autoprocessing).
In Nexus Data management window, browse to the session you want to process. Make sure the static trial has been processed so that labeling works for dynamic trials. Start up the gaitutils menu (see below). Select "Autoprocess session" or "Autoprocess single trial". The event detection is more accurate when processing the whole session, since it uses session level statistics.
You can improve the accuracy of forceplate detection by including foot lengths into your subject info (labeling skeleton template). In Nexus, click on the subject and select "Add parameter..." Add parameters called RightFootLen and LeftFootLen with the unit set as mm. Empty out all parameters and save the labeling skeleton as a new template. When taking subject measurements, measure the maximum length of the foot (or shoe) from heel to toe.
In addition to the graphical user interface, you can import the package in your own Python scripts. To try it out, launch e.g. the Spyder IDE that comes with Anaconda and run some of the examples below. Note that you have to start the Python interpreter in the gaitutils environment - if you installed Anaconda, the Windows menu should already have an entry that runs Spyder in the correct environment.
To do your own data processing in Python, you can extract trial data as numpy arrays.
Load a gait trial in Nexus. Run at least reconstruct, label and the Plug-in Gait model. Also mark some foot strikes and toeoffs (at least one gait cycle).
Loading the trial into Python:
from gaitutils import trial
tr = trial.nexus_trial()
print tr
Result:
<Trial | trial: 2018_11_14_seur_paljal_AH02, data source: <ViconNexus.ViconNexus instance at 0x000000000DE62648>, subject: Aamu, gait cycles: 6>
Extracting some marker data as Nx3 NumPy array:
t, mdata = tr.get_marker_data('RASI')
Extracting Plug-in Gait outputs:
t, mdata = tr.get_model_data('LPelvisAnglesX')
These will give frame-based data for the whole trial. t gives the frame number and has length equal to the data. To get data normalized to the first gait cycle, do:
t, mdata = tr.get_model_data('LPelvisAnglesX', 0)
Note that cycle numbering is 0-based. Now t is the percentage of gait cycle 0..100% and mdata is the normalized LPelvisAnglesX variable.
get_cycles can be used to get a specific gait cycle. For example, to normalize to first cycle with right context and forceplate contact, do:
cycles = tr.get_cycles({'R': 'forceplate'}) # returns all gait cycles on R that start with forceplate contact
cyc = cycles[0] # pick the 1st one
t, mdata = tr.get_model_data('LPelvisAnglesX') # extract cycle normalized data
The plotter supports a number of predefined layouts such as Plug-in Gait lower body kinematics. It handles normalization of data etc. This example plots lower body kinematics and kinetics from two c3d files using the matplotlib backend.
from gaitutils.viz import plots, show_fig
c3ds = ['data1.c3d', 'data2.c3d']
fig = plots.plot_c3ds(c3ds, layout_name='lb_kin', backend='matplotlib')
show_fig(fig)
The first import of the package (see 'Verification' above) should create a config file named .gaitutils.cfg in your home directory. You can edit the file to reflect your own system settings. You can also change config items from the graphical user interface (go to File/Options) and save either into .gaitutils.cfg (will be automatically loaded on startup) or some other file.
The most important settings to customize are described below, by section:
If you want to plot normal data for Plug-in Gait variables, edit normaldata_files to reflect the path to your normaldata file. .gcd and .xlsx (Polygon normal data export) file formats are supported.
Set devname to name of your EMG device shown in Nexus (for example 'Myon EMG'). When reading data from Nexus, analog devices cannot be reliably identified except by name. This setting does not affect reading c3d files.
channel_labels has the following structure: {'ch1': 'EMG channel 1', 'ch2': 'EMG channel 2', ...} Edit ch1, ch2 etc. to match your EMG channel names (as shown in Nexus). Edit the descriptions as you desire. Partial matches for channel names are sufficient, e.g. if you have a channel named 'RGas14' in Nexus you can specify the name as 'RGas'. In case of duplicate names, there is a warning and the shortest matching name will be picked.
default_model_cycles and default_emg_cycles specify which gait cycles to plot. The options are
-
'all': plot all gait cycles -
'forceplate': plot all cycles that begin on valid forceplate contact -
'1st_forceplate': plot first forceplate cycle -
0: plot first cycle (NOTE: explicit cycle numbering is zero-based!) - A list, e.g.
'[0,1,2]': plots first to third cycles - A tuple, e.g.
(forceplate, 0): plot forceplate cycles, or if there are none, first gait cycle
Set eclipse_write_key to e.g. 'DESCRIPTION' to automatically update Eclipse fields after processing. Set it to None if you want to leave the Eclipse fields alone. The enf_descriptions determines what to write into the Eclipse field.
Set events_range to limit automatically marked events to certain coordinate range in the principal gait direction.
Layouts defines the predetermined plotting layouts. Defaults include layouts such as
lb_kinematics = [['PelvisAnglesX', 'PelvisAnglesY', 'PelvisAnglesZ'],
['HipAnglesX', 'HipAnglesY', 'HipAnglesZ'],
['KneeAnglesX', 'KneeAnglesY', 'KneeAnglesZ'],
['AnkleAnglesX', 'FootProgressAnglesZ', 'AnkleAnglesZ']]
This would be 4 rows and 3 columns of PiG variables. Rows are inside the inner brackets, separated by commas. You can add your own layouts. The variables can include any PiG variables and EMG channels.
To update, give the command
pip install --upgrade https://github.com/jjnurminen/gaitutils/archive/master.zip
Occassionally it may be beneficial or necessary to upgrade the dependencies as well. Unfortunately, there's currently no easy way to do this. The best way may be to simply delete the whole environment with
conda env remove -n gaitutils
and reinstall via conda env create -f environment.yml
Create a file called .bashrc in your home directory. Put the following lines there:
. /c/Anaconda2/etc/profile.d/conda.sh
conda activate gaitutils
These commands will activate the gaitutils enviroment whenever you open git bash. Change c/Anaconda2 to your Anaconda install directory. c is the drive letter.
gaitutils needs the btk package to read c3d files. A 64-bit version for Python 2.7 is bundled. If you prefer to run 32-bit Python, you need to install btk yourself.
Download and run the installer from https://pypi.python.org/pypi/btk/0.3#files. The btk installer always puts the package into the conda root environment. Thus, after installation you need to copy the folder C:\Anaconda2\Lib\site-packages\btk into C:\Anaconda2\envs\gaitutils\Lib\site-packages\btk (modify paths depending on where you installed Anaconda)
The options cannot contain extended characters (i.e. outside of the ASCII set). The reason is that they are parsed using the ast module which cannot be easily be made to produce Unicode (https://bugs.python.org/issue35777). This will probably be fixed only when moving to Python 3.