Knowledge Base

Subjects Per Arena

Aim

To specify the number of subjects that are present in each arena during a trial. This setting is valid throughout the experiment, and cannot be changed after you have acquired the first trial.

Procedure

1. Choose Setup > Experiment Settings.
2. Next to Number of Subjects per Arena, select the number of subjects that are present in each arena simultaneously. If you intend to use the Deep Learning technique for body point detection, you can apply it to one or two subjects per arena.
3. Under Subject Roles, enter the role of the subjects or accept the default ones (Subject 1, Subject 2, etc.).

Subject Roles

To modify the subject's role name, right-click a name, select Rename and type in the new name. Enter generic role names; for instance in a Resident-Intruder test with two animals, enter Resident and Intruder, or Mutant and Wild Type.

Do not enter the ID of the subjects you are going to test. You can specify the ID of your subjects as an independent variable.

If you use the Deep Learning technique to track two subjects in an arena, the software does not know which role belongs to a specific individual. So it may happen that the resident subject is labeled Resident in one trial, and Intruder in another trial. To correct this, open the Track Editor and swap the subjects in the trial where the resident subject is labeled as Intruder.

Notes

• With the Base version of EthoVision XT you can track one subject per arena.
• With the Social Interaction Module, you can track up to 16 subjects per arena. Mind that this is a technical limit; the actual number of subjects that you can track depends on other factors. When using color markers to discriminate between individuals, it may be difficult to discriminate between 16 different color marks depending on the light conditions.
• To change the number of subjects per arena after acquisition, either delete the trials or make a copy of the experiment with a different name (File > Save As) and delete all trials.

Tracked Features

Aim

To specify which feature of the subject body is tracked. This choice affects the X,Y coordinates resulting in a track.

Procedure

1. Choose Setup > Experiment Settings.
2. Under Tracked Features, choose the option that applies to your experiment.

Center-Point Detection

To track only the geometric center of the subject detected (or the part of its body being detected). For example, in an open field or Morris water maze test.

Center-Point, Nose-Point and Tail-Base Detection

Tracking the nose-point is essential in, for example, a Novel Object Recognition test or in a Social Interaction test to determine how often and how long your subject touches the object of interest or follows and interacts with the other subject.

Also select this option:

• When you track two or more rodents per arena, marked with colors.
• When you want to use the Behavior Recognition function.

Color Marker Tracking (Treat Marker as Center Point)

If you choose this option, EthoVision XT will only detect the color marker, and track its geometric center. EthoVision XT won't extract the position of body points and any information about the subject's body posture. Choose this option for social interaction tests where you do not need to track nose and tail base (e.g. color-marked insects or fish).

Body Point Detection Technique

Aim

To choose which technique EthoVision XT uses to detect the nose-point and the tail-base points of your subjects.

Prerequisites

• In the Experiment Settings, under Tracked Features, you selected Center-point, nose-point and tail-base detection.
• The camera must be placed overhead.

Procedure

1. Choose Setup > Experiment Settings.
2. Under Body Point Detection Technique, choose the option that applies to your experiment.

Contour-Based

This technique uses foreground/background segmentation based on conventional image processing. The center-point, the nose-point and the tail-base point are derived from the detected body contour. This technique is suitable for any animal with an elongated body and pointed snout, for example rodents, fish, and certain insects.

Note: Contour-based is used by default in older EthoVision XT versions.

Deep Learning

If you choose this option, the nose-point and the tail-base point are detected using a trained neural network. The center-point is detected based on the contour of the detected subject, as described above (except for when there are two subjects in the arena; in that case the center point is also found using the neural network).

Important: Deep Learning is currently limited to rodents, and for up to two subjects. If you want to use the Deep Learning technique, consider that there are specific restrictions and hardware requirements. See also:

• Deep Learning: Basics
• Deep Learning: Requirements

Notes

• If you chose Center-point as the tracking feature, the center-point is always detected with the Contour-based technique.
• You cannot use the Deep Learning technique combined with Behavior Recognition.
• When you select Deep Learning, you may see this message: The graphics card driver is outdated or not installed or the graphics card does not support CUDA. It is possible that the graphics card is too old, or the graphics card driver is not up-to-date. See Deep Learning: Requirements.