Overview

This node parses the output of "License Plate Recognition" model to extract the license plate information.

This node requires AI Model Node (Vehicle Detection model) -> Model Inference Node (License Plate model) -> Track Objects Node -> Model Inference Node (License Plate Recognition) prior to it in order to function properly.

Inputs & Outputs

Inputs : 1, Media Format : Raw Video
Outputs : 1, Media Format: Raw Video
Output Metadata : None

Properties

Property	Description	Type	Default	Required
`display_info`	Controls whether license plate recognition information is displayed on the video frame	bool	true	No
`objects_to_associate`	Object classes to associate detected license plates with. Detected license plates within these object types will be associated with that object.	model-label	"car,vehicle,truck"	No
`watchlist`	Comma separated list of license plates to watch for	string	null	No
`watchlist_fuzzy_match`	If enabled, only matches license plates where differing characters look visually similar (e.g. 0 vs O, 1 vs I). The number of differences must still be within the tolerance limit.	bool	false	No
`watchlist_tolerance`	Number of characters that license plates can differ from watchlist entries	number	0	No
`detection_buffer`	Time in seconds that a license plate must be present before reporting results in metadata	float	0.1	Yes
`rejection_buffer`	Time in seconds during which objects that leave and re-enter the scene will be ignored. Increase to reduce duplicate alerts for a given object	float	5.0	Yes

Metadata

Metadata Property	Description
`nodes.<node_id>`	License plate information as described in the JSON below. \n \n`<node_id>` for License Plate Detection Nodes is of the form `annotate_lpr_edgeX` (ex. `annotate_lpr_edge1`)

"nodes":{
    "annotate_lpr_edge*":{
        "type":"annotate_lpr_edge",
        "license_plates_entered_delta":"<int>",
        "license_plates_exited_delta":"<int>",
        "watchlist_match_delta":"<int>",
        "license_plates_count":"<int>",
        "license_plates":{
            "<object_tracking_id>": {
                "plate":{
                    "type":"Plate",
                    "score":<float>,
                    "props":{
                        "plate":[
                            {
                            "value":"<license_plate_number>",
                            "score":<float>
                            }
                        ]
                    }
                }
            }
        }
    }
}

Format

Key	Type	Description
`license_plates_entered_delta`	Integer	Number of new license plates detected since last frame
`license_plates_exited_delta`	Integer	Number of license plates that left since last frame
`watchlist_match_delta`	Integer	Number of new license plates that matched the watchlist since last frame
`license_plates_count`	Integer	Total number of license plates in the view right now
`license_plates`	List of object IDs	Information about each detected and recognized license plate. \n \n`object_tracking_id` : Unique identifier for a specific object, as specified by `object.id` property (see Track Objects Node \n \nPlease check the `json` example for more details.

Objects metadata augmentation

The following information is added to the detected object's "attributes" array:

"class_id" field	"label" field	"probability" field
10400	The recognized license plate (string)	LP recognition confidence

"objects": [{
    "id": 5750484150146564100,
    "label": "car",
    "class_id": 0,
    "probability": 0.98,
    "rect": {
        "width": 47,
        "top": 201,
        "left": 656,
        "height": 25.
    },
    "attributes": [{
        "label": "ABC1234",
        "class_id": 10400,
        "probability": 1.0,
    }]
}]