---
title: "Understand object tracking in Shogun Live"
canonical: "https://help.vicon.com/space/ShogunLive121/1253212206/Understand%20object%20tracking%20in%20Shogun%20Live"
format: markdown
---
With Shogun 1.6 and later, you can use one of two pipelines to track objects and subjects. You can choose to use either the **standard **pipeline (the default option) or from an object’s Properties, select the **ObjectTracker **pipeline.
- The **standard **pipeline is the conventional approach to tracking, which requires computing reconstructions on every frame, labeling them, and then fitting the subject/object model to those labeled reconstructions.
- The **ObjectTracker **pipeline is a low-latency approach to tracking that enables a rigid object's pose to be updated using camera centroids. This means the reconstruction step can be bypassed during tracking, which reduces the latency.
The
**
ObjectTracker
**
pipeline provides the following methods for filtering tracking data:
- **
OneEuro
**
filter is a low pass filter that filters noisy data in real time.
- **
MotionPrediction
**
monitors and applies different motion models to data in real time, ensuring smooth data during predictable movements.
For more information about object tracking, choosing the most suitable pipeline and further details about the pipelines and the related object presets, see the following topics:
> Macro (toc)
For information on how to apply object tracking to props, see [Use object tracking](https://vicon-help.atlassian.net/wiki/spaces/ShogunLive121/pages/1253212375).
##
Choose the appropriate pipeline
The pipeline to use for tracking depends on what is being tracked:
- For rigid body objects, you can choose to use either the standard or ObjectTracker pipeline (the benefits of each approach are explained in the following sections).
- For all other objects or subjects, use the standard pipeline.
### When to use the standard pipeline
Use the standard pipeline, also known as the "Full-body" reconstruction-based approach, if you are tracking:
- Subjects (for example, performers or actors)
- Props, including:
- Multi-segment props
- Semi-rigid props
- Rigid bodies
Props held by a subject (for example, an actor holding a sword) are better tracked using this pipeline as it is easier for the system to handle any ambiguities between the prop and actor markers. This reduces the likelihood of mislabeling between prop markers and subject markers.
### When to use the ObjectTracker pipeline
Use the **ObjectTracker** pipeline if you are tracking only rigid bodies.
While you can use the standard pipeline to track rigid bodies, if you require the lowest possible latency (for example, camera tracking in ICVFX), use the ObjectTracker pipeline.
In general, ObjectTracker keeps better track of rigid-body props in situations where camera coverage is low. This pipeline also offers more functionality, including jitter reduction, smoothing, and support for motion models.
## Additional pipeline information
ObjectTracker is an alternative set of algorithms based on computing the 6DoF pose of the object directly, using 2D centroid data. This approach offers the following advantages:
- Shogun can track the object into parts of the volume where the standard pipeline may not be able to form enough reconstructions.
- Latency is minimized as there is no need to wait for reconstruction to finish before an object pose is obtained for a given frame.
The reconstructions are used by the ObjectTracker to boot (initialize) an object pose.
However, these reconstructions are not needed for frame-to-frame tracking, enabling the ObjectTracker to generate results even when the reconstructor drops frames.
> ℹ️ **Note**
> ℹ️ The Shogun interface always shows the standard output. As a result, when the reconstructor (or labeler/solver) is forced to drop frames, this is indicated in the time bar beneath your workspace. However, the ObjectTracker does not (usually) drop these frames as it is less computationally expensive.
> 
If you are streaming the outputs, use the following ports:
- Use Port 801 for standard pipeline data.
- Use Port 804 for ObjectTracker pipeline data.
For more information on streaming data, see the *[Streaming via Vicon DataStream SDK](https://vicon-help.atlassian.net/wiki/spaces/ShogunLive121/pages/1253212318/MCP+review+in+Shogun+Live#StreamingDataSDK)* section of *MCP review in Shogun Live* in *Getting Started with Shogun Live*.
> Macro (anchor)
## Object Preset settings
You can adjust ObjectTracker settings by using **Object Presets**. (For information on how to work with object presets in Shogun Live, see [Create and apply object presets](https://vicon-help.atlassian.net/wiki/spaces/ShogunLive121/pages/1253212375/Use+object+tracking#ObjectPresets).)
Within the Object Preset management window you can set what percentage of markers must be reconstructed to boot an object, and apply denoising with a **OneEuro** filter or by using **MotionPredictions**.
Settings that you can adjust in an Object Preset for a selected object are as follows:
> Macro (scroll-tablelayout)
| Setting Name | Description |
| --- | --- |
| Entrance Threshold | Minimum proportion of markers that must be visible before an object is booted.
Note that this applies to the selected object and overrides the Entrance Threshold that is set in the Object Tracking section of the Processing panel. |
> Macro (scroll-pagebreak)
### Denoising - OneEuro
The One Euro filter is a low pass filter for noisy data. Settings include cut-off values for translation and rotation and their velocity.
Three presets are available:
**Low - **Output pose will be close to raw pose but may still show jitter.
**Medium - **Provides a balance of **Low** and **High** presets.
**High - **Output pose will be very smooth but not as close to raw pose, pose will not respond to fast movements quickly.
> Macro (scroll-tablelayout)
| Setting Name | Description |
| --- | --- |
| Translation Min Cut-Off | Translation motion below this frequency will not be filtered. |
| Translation Beta | Controls the object translation velocity at which filtering will not occur. |
| Rotation Min Cut-Off | Rotation motion below this frequency will not be filtered. |
| Rotation Beta | Controls the object rotation velocity at which filtering will not occur. |
> Macro (scroll-pagebreak)
### Denoising - MotionPredictions
Motion Models are a group of models that describe how an object moves over time which can be applied to data that is moving within expected amounts. Shogun provides three models: constant pose, constant velocity, and constant acceleration.
The Motion Models are managed by a transition manager which enables smooth transitions between all models and no model being applied.
Two presets are available:
**VProd Low Noise - **for use in a well setup system with little noise.
**VProd All Rounder - **higher tolerance values, for use in noisier systems (recommended).
| Setting Name | Description |
| --- | --- |
| Motion Model Order | Numbers 0 - 3, corresponding to which motion models can be applied to the data.
0 = off
1 = off, constant pose
2 = off, constant pose, constant velocity
3 = off, constant pose, constant velocity, constant acceleration
Constant acceleration requires Sequential Weighting Look Ahead (found in the Object Tracking section of the Processing panel) to be on. |
| Translation Drift Tolerance
Rotation Drift Tolerance | Prevents a given motion level from being selected if (a) the RMS fitting errors is above that threshold, or (b) if the distance between the raw estimate and the filtered pose is above that threshold. |
| Motion Estimation Duration | The filtered motion is smoother with larger time windows, as long as the motion remains predictable.
If the motion is unpredictable, the prior level of 0 is chosen and the filtering stops after the transition period. |
| Motion Transition Duration | Time it takes to switch between different motion prior levels.
Shorter times cause sharper changes in the data when switching motion model. |