> For the complete documentation index, see [llms.txt](https://docs.theiamarkerless.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.theiamarkerless.com/theia3d-documentation/theia3d-dropdown-menus/settings-menu/analysis-preferences.md). # Analysis Preferences

The Analysis preferences pane contains advanced options and parameters relating to how people and objects are tracked, skeleton modelling, and 3D bounding box options *** ## Video Parameters *** #### **Analysis Frame Range**

First and last frame to analyze (inclusive). Modified frame range values are included when preferences are saved. **Default:** full trial length *** #### **Image Matte Percentage**

Image exclusion border size. Image matte area is displayed as a grey border around the camera views when active. The greyed-out portions of the videos will not be used when running the analysis, allowing poorly calibrated image borders to be ignored. Image matte exclusion area is not applied during lens calibration. **Default:** 3 *** ## Tracking Parameters *** ### People Tracking Parameters

People Tracking Parameters adjust the methods used to identify and track unique people throughout the duration of the movement trial. These options do not impact the skeletal modelling applied to the kinematic outputs, as they relate only to the identification of people. *** #### Max People

Maximum number of people to track. Options include No Max and integers 1-10. **Default:** No max *** #### Person Tracking Mode

Select the method for determining person tracking priority. Run Analysis (without 2D) must be performed in order to update person tracking after modifying this setting. * **Most Visible:** Person identification and tracking performed by prioritizing people who are visible in >75% of the total frames from all cameras throughout the entire trial, and ordering them by their distance to the global coordinate system origin. * **Closest to Origin:** Person identification and tracking performed by ordering all people by their minimum distance to the global coordinate system origin throughout the entire trial. For example, if a person walks directly over the origin, they will likely be identified as person 0. * **Order of Appearance:** Person identification and tracking performed by numbering people in order of appearance within the capture volume. **Default:** Most Visible *** #### **Remove stale IDs**

Remove any person IDs for people who have not been tracked for the selected frame interval. An example usage is to allow trials where multiple unique people sequentially enter then exit the capture volume one by one to be automatically assigned unique person IDs. **Default:** OFF **Default frames (when ON):** 100 *** #### **Track Rotating People**

Improve tracking of rotating and non-upright people, with a small increase to processing time. Default: OFF *** ### Objects Tracking Parameters

{% hint style="info" %} Objects tracking parameters are available for users with object tracking license add-on features; these features are not included in base Theia3D licenses. {% endhint %} Theia3D tracks linked objects, which must be associated with a tracked person (e.g. baseball bat), and free objects, which are independent from tracked people (e.g. baseball). *** #### Track Linked Objects

Enable the tracking of linked objects, e.g. baseball bats. **Default:** OFF *** #### Track Free Objects

Enable the tracking of free objects, e.g. baseballs. **Default:** OFF *** #### Single Moving Object

Track only one moving free object by identifying and retaining the longest tracked free object trajectory. This can prevent additional ghost objects from being detected and tracked. **Default:** OFF *** #### Remove Stationary Objects

Remove all stationary objects from the scene. This can provide cleaner data, avoiding extra free objects from being tracked. **Default:** OFF *** #### Smoothing Frequency

Adjust the cutoff frequency for the smoothing applied to the tracked object. This should be adjusted based on the movement that the object undergoes. Linked and Free objects' smoothing frequency can be adjusted separately. **Default:** * Linked: 50 Hz * Free: 100 Hz *** #### Advanced Object Definition Linked objects have additional Advanced Object Definition options that are accessible via the gear icon in the Smoothing Frequency table.

*** **Box Growth** Scaling value for the linked object detection boxes. Typically does not require adjustment, but can be increased to expand the region used when attempting to track object points. **Default:** 1.4 *** **Point Smoothing** Adjust the cutoff frequency for the smoothing applied to the object key points, prior to whole-object smoothing. **Default:** * Base (Baseball\_Bat type): 20 Hz * Tip (Baseball\_Bat type): 60 Hz *** ### Skeleton Tracking Parameters

Skeleton Tracking Parameters adjust the kinematic model that is used to track the captured movements. *** #### **Use Saved Model**

When not in use, the Theia's generic skeletal model will be scaled during Solve Skeleton to fit the person being tracked. When enabled, a previously saved scaled model can be used by the inverse kinematics algorithm to ensure identical model scaling. Select the ***Use Saved Model*** toggle and the ***Browse*** (folder icon) to select the model file to be used. Note that this option is only available when Max People is 1. **Default:** OFF *** #### **Kinematic Model**

Kinematic Model selection determines the underlying structure of the inverse kinematic model that is applied when solving for the pose throughout the movement trial. All kinematic model options have the same joint constraints, but are made up of different kinematic segment chains. Models that are made up of more kinematic chains (e.g. the Head, Arms, Torso, and Lower Body Model) will result in reduced tracking dropout under conditions where tracking is not possible, such as significant occlusion. For example, a fully occluded left hand would result in: full body dropout when using the Full Body Model, upper body dropout when using the Separate Upper and Lower Body Model, and left arm dropout when using the Head, Arms, Torso and Lower Body Model. **Default:** Separate Upper and Lower Body Models **Recommended:** Head, Arms, Torso and Lower Body Model *** #### **Full Body Model** Uses a single, whole-body IK chain. See [Full Body Model Description](/theia3d-documentation/theia-model-description/full-body-model-description.md) for a detailed description of this model. {% hint style="info" %} Full Body Model must be used if saving FBX format pose output files. {% endhint %} *** #### **Separate Upper and Lower Body Model** Uses separated IK chains for the lower body (pelvis and legs), and upper body (torso, head, arms). No abdomen or neck segments. See [Separate Arm and Head Model Description](/theia3d-documentation/theia-model-description/head-arms-torso-and-lower-body-models-description.md) for a detailed description of this model. *** #### **Head, Arms, Torso and Lower Body Model** Uses separated IK chains for the lower body (pelvis and legs), torso, arms, and head segments. No abdomen or neck segments. See [Separate Arm and Head Model Description](/theia3d-documentation/theia-model-description/head-arms-torso-and-lower-body-models-description.md) for a detailed description of this model. *** #### **3-DOF Knee**

If selected, the model used by the inverse kinematics algorithm will have three degrees of freedom at the knee (flexion/extension, ab/adduction, and internal/external rotation). If not selected, the model will have two degrees of freedom at the knee (flexion/extension and ab/adduction). **Default:** OFF *** ### Force Model Symmetry

Option to force inverse kinematic model symmetry after scaling. This will ensure that left/right segment pairs in a model are the same length. **Default:** OFF {% hint style="info" %} Note: that this currently only forces symmetry within a model not between models (i.e. if using separate left and right arm models they will not be made symmetric). {% endhint %} *** #### **Smoothing Freq. (Hz)**

The smoothing frequency used is based on the [GCVSPL method,](https://isbweb.org/resources/software-resources/137-signal-processing-software/494-gcvspl) which provides results equivalent to applying a double-pass Butterworth filter. Theia3D automatically fills gaps and smooths the 3D pose data for all individuals tracked in processed movement trials. The cutoff frequency of the lowpass filter used to smooth the pose from the inverse kinematics. The default GCVSPL cutoff frequency is 20 Hz, cutoff frequency provides some smoothing and noise reduction while generally being sufficiently high to avoid over-smoothing most movements.
**General Recommendations:** {% hint style="info" %} It’s important to refer to relevant literature wherever available to identify filter frequencies that are most appropriate for the specific movements being analyzed. {% endhint %} * For slow movements (e.g. sway, slow walking), a lower cutoff frequency around 6–12 Hz can be used. * For faster movements (e.g. running or jumping), a higher cutoff frequency around 10–20 Hz may be required. * Movements with very high segment velocities or accelerations such as baseball pitching or very dynamic changes of direction, cutoff frequencies above 20 Hz may be required. {% hint style="warning" %} If the smoothing frequency is set too low when processing very fast movements such as pitching, tracking dropouts may occur as the fastest moving segments are detected as outliers. If you encounter this situation, try increasing the smoothing frequency and using Solve Skeleton to implement the new setting, which may restore segment tracking. {% endhint %} *** #### **Show Warning**

When applying the filter using the selected smoothing frequency, Theia3D checks whether the applied smoothing frequency is appropriate for the movement and warns the user if they should consider adjusting the frequency. This test can occasionally produce false positive warnings, so these warnings can be disabled if desired.

*** ## Analysis Bounding Box ***

### **Display/Use** Enables the 3D Analysis Bounding Box for use, which restricts person tracking to within a specified 3D volume. This allows people who are visible but not of interested to be ignored, such as the experimenter or other observers. ***Run Analysis (without 2D)*** must be performed in order to update person tracking and skeleton visibility after adjusting this setting. *** ### **Use Camera Locations** The 3D camera locations will be used to establish the edges of the analysis bounding box, rather than the x, y, and z origin positions and length, width, and height dimension definitions. * ***Origin X:*** Position of the center of the bounding box along the global coordinate system X-axis. * ***Origin Y:*** Position of the center of the bounding box along the global coordinate system Y-axis. * ***Origin Z:*** Position of the center of the bounding box along the global coordinate system Z-axis. Minimum value is half the bounding box height. * ***Length:*** Bounding box dimension along the global coordinate system X-axis. * ***Width:*** Bounding box dimension along the global coordinate system Y-axis. * ***Height:*** Bounding box dimension along the global coordinate system Z-axis. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.theiamarkerless.com/theia3d-documentation/theia3d-dropdown-menus/settings-menu/analysis-preferences.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.