Knowledge Base

Advanced Detection Settings: Behavior Recognition

To Adjust Behavior Recognition Settings

1. In the Detection Settings pane, click Behavior Recognition.
2. If you work with video, play the video up to a frame where the subject is walking normally, and its hind limbs can be partially seen. It is important that the animal's body is not contracted or stretched, and that nose- and tail-base points are correctly detected. If you track live, wait until the animal shows a normal walking posture.
3. In the Behavior Recognition Settings window, click the Grab button.
4. A still image appears showing the detected subject's contour and the detected body points. You can update the grabbed image at any time:
   • If you track from video files, position the video to another frame, and click Grab.
   • If you track live, wait until the posture of the animal is as described above, and click Grab.
   EthoVision XT only stores the image grabbed last.
5. In the Behavior Recognition Settings window, make sure that the calculated Subject length is greater than 60 pixels (55 for mice), and that the Posture index is between 70 and 90. If the Subject length is smaller than 60 pixels (55 for mice), move the camera closer to the animal, or use a higher video resolution. The subject length must not exceed half the arena size.
6. Click OK to close the Behavior Recognition Settings window.

To Enter Specific Size Values (Optional)

If you know specific size values (for example, from a previous experiment using the same animal size, camera, lighting, camera-arena distance and the same calibration), click Manual in the Behavior Recognition Settings window and in the Manual Settings window enter the following values:

• Subject area (in distance unit square)
• Center-nose length (in distance unit)
• Center-tail length (in distance unit)
• Posture (between 70–90)

Then click OK. The Behavior Recognition Settings window says: No image saved: Size settings were manually set.

• Subject size is expressed in the unit selected in the Experiment Settings.
• The value of Subject length in the Behavior Recognition Settings window is the sum of Center-nose length and Center-tail length, expressed in pixels. If this value is lower than 60 (55 for mice), when opening the Acquisition screen an error message appears. To increase subject length, move the camera closer to the animal, or use a higher video resolution.

Making Size-Dependent Detection Settings

Accurate recognition of behavior is based on subject size settings. Since apparent size increases with the subject age, all being equal, we advise you to create detection settings specific for a certain age class. Each Detection Settings profile can only be used for a limited time. For example, for Wistar rats, a Detection Settings profile for rats that are 3–5 weeks old, which can be used about one week, and a Detection Settings profile for rats older than 5 weeks, which can be used for two weeks.

Subjects should not vary in size for more than 10%. If that happens, create more Detection Settings (for example, one for smaller animals and one for larger animals).

Important: EthoVision XT shows a warning message in the following cases:

• When the sample rate set is lower than 25 or higher than 31 samples/s.
• When the Subject length is smaller than 60 pixels for rats, or 55 pixels for mice.
• When the animal is larger than the arena.

Other Settings for Behavior Recognition

Smoothing

See Advanced detection settings: Smoothing.

Subject Contour

For optimal results, we recommend selecting Erosion and then Dilation to remove the tail from the detected body. See Advanced detection settings: Subject contour.

Subject Size

Choose the option depending on the method for estimating the body points.

• If you select Rodents / Default: See Advanced detection settings: Subject size (one subject per arena).
• If you select Rodents / For occlusions: See Advanced detection settings: Subject size (multiple animals per arena).

Subject Exposure

When using Behavior recognition, the amount of light that the camera receives from the subject is even more important than usual. See Subject exposure.

Subject Exposure

Aim

To obtain a balanced image of the subject. This is of critical importance when using Behavior recognition.

Prerequisites

• Your experiment is set for Behavior recognition.
• You open the Detection Settings.

Procedure

1. Play the video or let the subject walk in the arena.
2. In the Detection Performance window, locate the Subject Exposure indicator.
3. Make sure that the Exposure is Good when the subject has been in all parts of the arena.
4. When the image is overexposed or underexposed, the subject looks too bright or too dark, respectively. The details of the fur are hardly visible. Try the following:
   • To reduce the subject's exposure, close the aperture of the camera lens. Alternatively, for GigE and USB cameras, reduce the Exposure time.
   • To increase the subject's exposure, open the aperture of the camera lens or increase the Exposure time. If that is not possible, increase the Gain.
   For how to adjust the exposure and gain, see Adjust camera settings in EthoVision XT.

Notes

Check the exposure level when the subject is walking or sitting still. The subject's tail should not touch the sides of its body. If that occurs, the estimate of subject exposure may not be reliable. Wait until the subject's tail does not touch its body, and check the Exposure Level for a more reliable indication.