You are viewing an old version of this page. View the current version.
Compare with Current
View Page History
« Previous
Version 4
Next »
Description | The Pose Detection uses a neural network and detection sub-tools to determine each person's skeleton and detect poses that could indicate a potentially dangerous situation |
Detection sub-tools | You can create the following sub-tools on the basis of the Pose Detection: - Sitting person detection—detection tool triggers when there is a sitting person in the frame.
- Man down detection—detection tool triggers when there is a prostrate person in the frame.
- Hands up detection—detection tool triggers when there is a person with one or two hands raised in the frame. A hand is considered raised if the forearm is parallel to the back.
- Handrail holding detection—detection tool triggers when there is a person in the specified part of the frame who doesn't hold any of the specified handrails.
- People counter detection—detection tool counts objects in the specified area. Detection tool triggers when the number of objects reaches or exceeds the specified limit.
- Close-standing people detection—detection tool triggers when the distance between people in the frame exceeds the specified minimum value.
- People masking detection—detection tool masks people in the video image, doesn't trigger
|
Add-ons | For the Pose Detection and its sub-tools to work, you must install Neuro Pack add-on (see Installing DetectorPack add-ons) |