3D Object Tracking

The 3D Object Tracking recipe in Aivia detects objects (such as cells and nuclei), generates surface reconstructions, and tracks their movement in 3D+time volumetric images.

The recipe provides a count of the number of detected objects as well as morphological, intensity, and motility measurements of the detected objects.

On this page:

1 Parameters and Presets
- 1.1 Parameters
- 1.2 Presets
2 Tutorial
3 Measurements
4 Image Credits
5 Related Articles

Parameters and Presets

Parameters

Recipe parameters for 3D Object Tracking and their descriptions are summarized in the table below.

Preset Group	Parameter Name	Min Value	Max Value	Description

Preset Group	Parameter Name	Min Value	Max Value	Description
Detection	Image Smoothing Filter Size	1	100	Specifies the diameter of the filter that is used to smooth the input channel before further processing The available smoothing types are the following: Morphological Smoothing applies a morphological filter consisted of an average filter and morphological opening/closing operations based on the value of the Image Smoothing Filter Size. Average Filter Smoothing applies an average filter that outputs the average intensity value for each voxel across a circular region, with diameter specified by the value of the Image Smoothing Filter Size. Gaussian Filter Smoothing applies a Gaussian filter with a filter width specified by the value of the Image Smoothing Filter Size. Median Filter Smoothing applies a median filter that outputs the median intensity value for each voxel across a circular region, with diameter specified by the value of the Image Smoothing Filter Size.
	Average Object Radius (Remove Background only)	0	1,000 (px or µm)	Specifies the radius of a typical object in the image for object enhancement and background removal; a lower value will preserve smaller objects
	Min Edge Intensity	0	255 (8-bit) 65,535 (16-bit)	Specifies the minimum object intensity that is typically found at the edge of the object for detection; when Remove Background is enabled, this parameter value is used to specify the minimum object intensity on the enhanced image; a lower value will detect bigger and more objects
	Fill Holes Size	0	1,000,000 (px² or µm²)	Specifies the maximum size of gaps in detected objects that are filled; a lower value leads to the preservation of more holes in the detected objects
Partition	Object Radius	0	1,000 (px or µm)	Specifies the range of objects to be included in the analysis results based on the radius of the detected objects
	Mesh Smoothing Factor	0	10	Adjusts the amount of smoothing applied to the surface reconstructions of the detected objects; a lower value will generate surfaces with greater similarity to the input image
	Min Edge to Center Distance (Apply Partition only)	0	1,000 (px or µm)	Specifies the minimum distance from the center of an object to the edge that is touching its closest neighboring object; this parameter is enabled only when Apply Partition is enabled; a lower value will apply object partitioning more aggressively, resulting in smaller, more uniform objects
Tracking	Minimum Track Length	1	100	Specifies the minimum number of time frames before a detected object is considered a valid track; a lower value will generate more, and often shorter, tracks
	Maximum Search Distance	0	1,000 (px or µm)	Specifies the maximum distance for track-point matchmaking between successive time frames; a higher value will expand the search distance for fast-moving cells
	Motion vs Intensity	0	10	Adjusts the relative weighting between motion and object intensity for track-point matchmaking between successive frames; a value of 5 will apply equal weights to motion and intensity for matchmaking
	Track Lineage Option	Not applicable		Toggles tracking of object division and lineages
	Matchmaking Option	Not applicable		Toggles the tracking algorithm used for track-point matchmaking between time points; the available options are Greedy Matching and Hungarian Matching

Presets

There are three preset groups in the recipe: Detection, Partition and Tracking; each group has three pre-configured parameter groupings to help you get started on the analysis. The default preset values are in the following subsections.

Detection

Parameter Name	Low	Medium	High
Image Smoothing Filter Size	3	9	13
Average Object Radius	5 (px or µm)	20 (px or µm)	100 (px or µm)
Min Edge Intensity	10 (8-bit)	5 (8-bit)	3 (8-bit)
Min Edge Intensity	2,621 (16-bit)	1,311 (16-bit)	655 (16-bit)
Fill Holes Size	0	0	0

Partition

Parameter Name	Small	Medium	Large
Object Radius	2 - 5 (px or µm)	20 - 50 (px or µm)	100 - 300 (px or µm)
Mesh Smoothing Factor	0	0	0
Min Edge to Center Distance	2 (px or µm)	20 (px or µm)	100 (px or µm)

Tracking

Parameter Name	Motion	Mixed	Intensity
Minimum Track Length	2	2	2
Maximum Search Distance	5 (px or µm)	5 (px or µm)	5 (px or µm)
Motion vs Intensity	3	5	7
Track Lineage Option	Track Lineages
Matchmaking Option	Use Greedy Matching

Tutorial

Before beginning the tutorial, please download the 3D Object Tracking Demo image. For information on how to select presets or modify parameter values, please refer to the tutorial on how to use the Recipe Console.

Unzip the demo file and load the demo image, “3DObjTrackDemo.aivia.tif,” into Aivia.
In the Recipe Console, click on the Recipe selection dropdown menu and select the 3D Object Tracking recipe.
Click on the Small button for the Partition preset and the Intensity button for the Tracking preset. Leave the Detection preset as is for now.
Click on the Show Advanced Interface icon to expand the Recipe Console.
Under the Detection preset, click on the Switch Recipe Operations icon next to the Image Smoothing Filter Size parameter to show the list of available recipe operations; select the Skip Smooth Image option from the dropdown menu.
Under the Detection preset, click on the Switch Recipe Operations icon next to the Min Edge Intensity and Fill Holes Size parameters to show the list of available recipe operations; select the Remove Background option from the dropdown menu.
Change the parameters listed below to the specified values, leaving the others intact:
- Detection
  - Average Object Radius: 4
  - Min Edge Intensity: 3
  - Fill Holes Size: 1
- Partition
  - Mesh Smoothing Factor: 1
  - Min Edge to Center Distance: 4
Click the Start button or press the F4 key on your keyboard to begin applying the recipe to the image.

The surface reconstructions can be viewed in 3D View, while all tracks can be viewed in both Main View (2D) and 3D View. Please note that in Main View (2D) tracks that are out of the current plane are also overlaid on the image.

Results

3D Object Tracking tutorial results

Show Advanced Interface icon

Measurements

The 3D Object Tracking recipe generates morphological, intensity, and motility measurements for each detected 3D object as well as a count of the total number of 3D objects on the image. You can add additional measurements to the analysis results with the Measurement Tool in Aivia and view measurement definitions on the Measurement Definitions page. The measurements generated by the recipe are in the table below.

Morphology	Intensity	Position	Advanced

Morphology	Intensity	Position	Advanced
Path Length Velocity Angle Surface Area Volume Surface Area to Volume Ratio	Mean Intensity Max Intensity Min Intensity Total Intensity Std. Dev. Intensity	Total Time First Frame Last Frame Mean Velocity Direct Line Velocity Acceleration Magnitude Velocity Magnitude Centroid X Centroid Y Centroid Z	Object Count

Image Credits

Stegmaier J, Mikut R. (2017) Fuzzy-based propagation of prior knowledge to improve large-scale image analysis pipelines. PLoS One. 12(11):e0187535. doi:10.1371/journal.pone.0187535