Understand object evaluation

In Understand object booting, it was explained that unique marker configurations would facilitate efficient and accurate object initialization. However, following this guideline can be difficult under two common scenarios:

• When there are a large number of similarly sized objects, as unique marker patterns may be difficult to generate
• When using smaller objects, as the average distance between markers is proportionally smaller

To avoid any issues with object similarity, Tracker can provide an objective assessment of all active objects. Object evaluation is an automated process which runs in the background to systematically compare the similarity of the pattern of markers for each object that is enabled in the Tracking panel with every other enabled object, including itself. This can help to reduce any errors with object booting.

When you create, load or change objects, Tracker evaluates all objects and if there is a high likelihood of confusion between objects, it flags each object with a yellow warning triangle in the Tracking panel.

To view specific information about the type of similarity, hover the mouse pointer over the warning symbol.

For details about the way Tracker evaluates the similarity of objects and the actions you may need to take, see these topics:

How does object evaluation work?

Tracker's object evaluation feature compares each object that is enabled in the Tracking panel with every other enabled object, and displays a warning when a match between a pair of objects is detected. The warning tooltip indicates which other object (or objects) that the current object may be confused with, and the match distance (in millimeters). The match distance is the approximate average displacement between the object markers, when the two objects have been aligned to the closest matching pose.

The average match distance is controlled by the Object evaluation warning threshold (mm) setting in the Preferences (Set user and system preferences). A match distance lower than this setting will trigger an object confusion warning.

A match distance of 0 indicates that the object pair is identical (or to be more precise, the fraction of markers specified by the object's Entrance Threshold (see Why is the Entrance Threshold important?) is identical to a pattern of markers on the other object). Conversely, a large match distance indicates the objects are easy to distinguish, and unlikely to be confused.

Why is the Entrance Threshold important?

The concept of the Entrance Threshold was previously described in Understand object booting. This parameter is also used for object evaluation as it specifies the minimum proportion of markers to be used as part of the object evaluation process. In terms of the importance of Entrance Threshold for object evaluation, let's consider these examples again:

• If the Entrance Threshold is low for Object Evaluation, it will be more likely that objects will be flagged for similarity. If you have a 10-marker object with an Entrance Threshold of 0.3, two objects would only need to match only 3 markers on each to be considered similar regardless of how different they are as a whole.
• If the Entrance Threshold is high, a more thorough evaluation of an object's marker geometry when assessing similarity can be conducted.

There is a subtle but important distinction here; for object booting, you may want to use as low an entrance threshold that can reliably boot your objects but a high entrance threshold for object evaluation so you can do a more thorough assessment. While the entrance thresholds may end up being the same for both processes, they need not be synchronized and may allow each function to perform better when not synchronized.

As such, Tracker defaults to an entrance threshold of 1 for object evaluation so that all markers are considered when evaluating similarity and uses a separate entrance threshold to be used for booting. This should be suitable for the tracking scenarios where all markers (or a high proportion of markers) can be used for the booting of an object.

For details on how to change the Entrance Threshold for object evaluation, see Configuring object evaluation.

Examples of object similarity

To help understand object similarity, consider the following examples. Each example uses the default Tracker setting for object similarity (i.e. an entrance threshold of 1).

Different number of markers

Object A has 4 markers, while Object B has 5 markers:

• Object A matches object B, match distance = 0 (The match distance is the approximate average displacement between the object markers, when the two objects have been aligned to the closest matching pose.)
• Object B doesn't match object A (which doesn't have enough markers to meet the Entrance Threshold for object B).

If we reduced the object evaluation Entrance Threshold to 0.8 for object B, it would then match object A identically (with match distance 0).

Moved marker

Object A and object B both have 4 markers, one of the markers on object B has been moved. The distance between the markers is the marker match distance, as indicated on the above diagram.

• Object A matches object B with an average match distance of the marker match distance/4 (3 markers match exactly, with distance 0).
• Object B matches object A with the same average match distance.

Self-similarity (rotational symmetry)

Here we have rotated object A by 180° clockwise.

• Object A matches itself with average match distance of the marker match distance/2 (2 markers match exactly, with distance 0).

Rotational symmetry is a problem because it means Tracker will have difficulty in determining the correct orientation of the object. You would notice this as unpredictable rotational errors or 'flipping' the object when starting tracking.

Self-similarity (repeated marker pattern)

Here object A has 3 markers repeated in the same pattern - (1, 3, 4) matches (2, 5, 6) exactly.

This is not necessarily a problem if Entrance Threshold is set to 1, but if Entrance Threshold is set to <= 0.5 then Tracker could start tracking from either pattern subset, and cannot distinguish between the two. You would notice this as an unpredictable translational error when starting tracking.

To learn how to eliminate object similarity matches, see Resolving Object Similarity.

Resolving Object Similarity

If objects are confused with one another, physically adjust the placement of one or more markers on the affected objects to make their patterns distinct.

After one or more markers has been moved, to update the object evaluation and ensure correct tracking, in the Tracking panel make one of the following changes:

• Remove the current object from the Objects list and recreate a new object.
• Use the Remove Marker button to remove each marker that was physically moved and the Add Marker button to add it back to the object.

Both options ensure the correct relationship between the current marker locations and the local coordinate system of the object is maintained.

Configuring object evaluation

As mentioned, the default setting in Tracker is to set the object evaluation entrance threshold to 1 and not have it linked to the booting entrance threshold. However, in certain instances, it may not be desirable to use the default settings for object evaluation; that is, you may want to use an Entrance Threshold lower than 1. To do this:

• Open the Preferences dialog box (Settings > Preferences or Shift+P).

• In the User Preferences, scroll to the Objects section and select Object evaluation uses tracking entrance threshold.

  Now the tracking and object evaluation thresholds are the same.

To learn how to configure booting thresholds, see Understand object booting.

Control object evaluation

To turn object evaluation on and off or to change the sensitivity of the evaluation to object differences:

1. Open the Preferences dialog box (Settings > Preferences or Shift+P).
2. Scroll to the Objects section.

3. You can change the following settings:

   

   • Enable Object Evaluation - Turn object evaluation on or off: the default is selected (on). When selected, each object is compared to all the others for possible confusion.

     Important: If you have many objects or objects with many markers, evaluation can take a long time, so if you want to minimize latency, we recommend turning off Object Evaluation (see Control object evaluation).

   • Object evaluation step limit - Maximum number of iterations(steps) that are expended in evaluating each object pair. Increasing this value may enable the evaluation to find more potential problems, particularly for objects with many markers, but at the cost of increased computation time. The default limit is 1000 steps.
   • Object evaluation uses tracking entrance threshold - Controls which entrance threshold is used forobject evaluation. If enabled, object confusion evaluation uses the entrance threshold specified in the Processing panel or the object preset if one was set for an individual object. An entrance threshold less than 1 results in more object confusion warnings. If disabled, the entrance threshold for object confusion evaluation is set to 1 and all markers are used to evaluate similarities between objects. The default is disabled.
   • Object evaluation warning threshold - A warning is displayed if the match distance in millimeters between a pair of objects falls below this threshold. (The match distance is the approximate average distance that the object markers would have to move to exactly match the other object, or part of it.) You may want to adjust this setting so that it is higher than the typical level of noise (resulting in 3D positional jitter) in your volume. The default threshold is 3 mm.
4. Click OK to accept any changes and close the dialog box.