Smart Zoom
Pan and Zoom to cover specific objects detected by any AI model
Overview
The Smart Zoom
node allows for panning and zooming to cover specific objects detected by any AI model. This functionality is crucial for applications requiring focused attention on particular objects within a video frame.
Properties
Property | Description | Type | Default | Required |
---|---|---|---|---|
object_types | Objects to focus on. ex. car ,person ,face.mask . Use the object_label.class_label format for objects that also have a specific class. | model-label | null | No |
zoom_adjust_speed | Zoom adjust speed. Slider min: 0, max: 100. Larger is faster. | slider | 10 | No |
zoom_adjust_threshold | Don't adjust zoom unless a new zoom window differs from current one by more than this percentage. Slider min: 0, max: 100. | slider | 15 | No |
zoom_reset_interval | Reset zoom if no objects matching type are seen for this time. Slider min: 0, max: 100. | slider | 15 | No |
Output Metadata
This node does not explicitly output metadata but affects the zoom level of the video stream based on detected objects.
Updated about 2 months ago