Overview

The AI Model by Roboflow node allows for running a Roboflow AI Model inference on input frames, and adds detected objects to metadata. This functionality is useful for applications requiring object detection and recognition.

Inputs & Outputs

Inputs : 1, Media Format : Raw Video
Outputs : 1, Media Format: Raw Video
Output Metadata : Objects metadata

Properties

Property	Description	Type	Default	Required
model_id	Model alias or ID from Roboflow. Typical format is `{project_id}/{version}`.	string	null	Yes
model_type	Model type. Options: `detector`, `classifier`.	enum	detector	Yes
roboflow_api_key	Roboflow Private API Key (for inference) can be found at Account -> Settings -> Workspace -> Roboflow API in your Roboflow account.	string	null	Yes
inference_mode	Inference mode. Options: `full_frame` (Run inference on entire frame), `objects` (Run inference on specific object types, ex for classification).	enum	full_frame	Yes
objects_to_infer	Object types and classes to include. Leave blank to include all. Conditional on `inference_mode` being `objects`.	model-label	null	No
interval	Infer on every nth frame. 1 means infer every frame.	number	1	Yes
confidence_threshold	Enable to override the default minimum inference threshold for all classes. Slider min: 0, max: 1.0, step: 0.1.	slider-optional	0.5	No
iou_threshold	Increase the threshold to reduce potential duplicate detections of a single object. Slider min: 0, max: 1.0, step: 0.1. Conditional on `model_type` being `detector`.	slider-optional	0.5	No
min_object_size	Minimum object size, e.g., width x height. Conditional on `model_type` being `detector`.	string	null	No
reclassify_size_threshold	Reclassify a specific object if size changes by this percent. Only used when inference mode `objects`, and Track objects node is present before this node. Conditional on `model_type` being `classifier`.	number	50	No
max_classify_attempts	Attempt classification per object this many times before giving up if it yields no class results. Only used when inference mode `objects`, and Track objects node is present before this node. Conditional on `model_type` being `classifier`.	number	3	No

Metadata

Metadata Property	Description
`objects`	List of Objects detected by the Model inference nodes. See table below for the format of this property.

'objects': [{
    'id': 5750484150146564100,
    'label': 'car',
    'class_id': 0,
    'probability': 0.70000000149011612,
    'rect': {
        'width': 47,
        'top': 201,
        'left': 656,
        'height': 25
    },
    'attributes': [{
        'label': 'white',
        'probability': 0.9437278509140015,
        'class_id': 10
    }]
}]

Object Properties

Key	Type	Description
`id`	Long Int, Optional	If present, it is a unique ID assigned to this object by a Track Objects Node
`label`	String	Label for this object as outlined in Model Labels
`class_id`	Int	Unique id for this object's label.
`probability`	Float	Probability of detection
`rect`	Dictionary	Bounding box for this object. Contains: `left`, `top`, `width`, `height`
`attributes`	Dictionary	Object's classes, as identified by Classifier models chained to this Object Detection model. Contains: `label` : Class label, `probability` : Probability, `class_id` : Unique id for the class' label