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; see the figure below. It is important that the animal’s body is not contracted or stretched. Also, nose- and tail-base points are correctly detected.
If you track live, wait until the animal shows a posture like in the figure above.
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 that the posture of the animal is like that 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 (see the picture below for explanation):
▪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 then 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.
For optimal results, we recommend to select 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