Input and output format for the default Face Detection demo model.
This AI model is a small ~1MB SSD-style detector, trained to detect faces.
The input tensor dimension for this model is 320 wide by 240 high.
This model accepts the following extra input information:
Sensitivity threshold: NMS sensitivity.
Each detected face is identified using a bounding box represented by a vector: [x1, y1, x2, y2, score, class].
Position and size coordinates, to be used as a rectangular bounding box.
A confidence score, which helps retain only the most confident and accurate detections while suppressing weaker or redundant ones.
Class, in this case always "Face".
The following image shows an example of this model's output:
This model's detections can be combined with any of the built-in postprocessors, for example:
Loitering Detection: detect when an object stays in frame longer than a configured time threshold.
Left Behind Object Detection: detect objects left behind or removed compared to a reference frame.
Line Crossing Detection: detect or count objects that cross a defined line, and generate an event.
Object Counting: count bounding boxes per class and generate a counting event.
See Postprocessors for the full list and configuration details.
Last updated 13 days ago
