Overview

The Line Counter node keeps track of the number of objects that cross a virtual line in the video, the direction they cross it in, and adds the line counting metadata to the frame metadata. This node makes it easy to build common use cases such as People counting, Parking lot occupancy counting, etc.

This node supports Lines with one or more segments, allowing you to be as granular as you need for your counting needs.

This node requires a AI Model Node and a Track Objects Node before it in order to function properly.

Inputs & Outputs

Inputs : 1, Media Format : Raw Video
Outputs : 1, Media Format: Raw Video
Output Metadata : Line Counter Information

Properties

Property	Value
`objects_to_track`	Comma separated list of Detected Object labels to track, as specified in Model Labels ex. `car, person` Accepted formats: `object_label`: any object of this type, with or without a classifier attribute. Example: `car` `object_label.class_type`: any object of this type that has a specific classifier attribute. Example: `car.red` `object_label.`: any object of this type that has at least one classifier attribute. Example: `car.` (this will match `car.red`, `car.yellow`, etc)
`display_line`	Boolean. If line information will be displayed on the video stream Ex. `true` / `false`
`display_objects`	Boolean. If objects will be displayed on the video stream Ex. `true` / `false`
`lines`	Semicolon separated list of lines in the video across which this node tracks these objects. Each line can have multiple segments and can be defined by two or more points (`x1,y1,x2,y2,x3,y3`). Format: `line1_x1,line1_y1,line1_x2,line1_y2; line2_x1,line2_y1,line2_x2,line2_y2` Ex: `10,10,100,100; 200,200,300,300`
`line_labels`	Comma separated list of labels for each ROI in the `rois` list above. Format: `label1, label2` Ex: `door, window`
`dir1_label`	Label for Direction 1 (Red color in the Lines widget). Optional. Ex. `entry`
`dir2_label`	Label for Direction 2 (Red color in the Lines widget). Optional. Ex. `exit`
`persistent_storage`	Boolean. If true, the following analytics will be stored in disk and restored when the pipeline restarts: [line_label]['total_objects_crossed'] [line_label]['dir1_objects_crossed'] [line_label]['dir2_objects_crossed'] Ex. `true` / `false`

Metadata

Metadata Property	Description
`nodes.<node_id>`	Describes the Lines monitored by this node, and their properties. Format : as defined in the table below. `<node_id>` for Line Counter Nodes is of the form `annotate_line_counterX` (ex. `annotate_line_counter1`)

Example

"nodes": {
    "annotate_line_counter1": {
        "type": "annotate_line_counter",
        "lines": {
            "<line_label>": {
                "dir1_label": "entry",
                "dir2_label": "exit",
                "coords": [[<point1_x>, <point1_y>],[<point2_x>, <point2_y> ]],
                "total_objects_crossed": <number>,
                "total_objects_crossed_delta": <number>,
                "dir1_objects_crossed": <number>,
                "dir1_objects_crossed_delta": <number>,
                "dir2_objects_crossed": <number>,
                "dir2_objects_crossed_delta": <number>,
                "cur_dir1_objects": [ <object_tracking_id>,<object_tracking_id> ],
                "cur_dir2_objects": [ <object_tracking_id>,<object_tracking_id>  ]
            }
        }
    }
}

Format

Key	Type	Description
`<line_label>`	Array of dictionaries	Contains information about this specific line
`<line_label>.coords`	Dictionary	Contains the coordinates for this line `point1_x`, `point1_y` : Coordinates of one endpoint `point2_x`, `point2_y` : Coordinates of the other endpoint
`<line_label>.total_objects_crossed`	Integer	Number of objects seen crossing this line since the start of the pipeline
`<line_label>.total_objects_crossed_delta`	Integer	Number of objects seen crossing this line between last frame and this frame (both directions)
`<line_label>.dir1_objects_crossed`	Integer	Number of objects seen crossing this line, in one direction since the start of the pipeline
`<line_label>.dir1_objects_crossed_delta`	Integer	Number of objects seen crossing this line between last frame and this frame in the direction 1
`<line_label>.dir2_objects_crossed`	Integer	Number of objects seen crossing this line, in the other direction since the start of the pipeline
`<line_label>.dir2_objects_crossed_delta`	Integer	Number of objects seen crossing this line between last frame and this frame in the direction 2
`<roi_label>.cur_dir1_objects`	List of object IDs	Information about the objects currently crossing the line in the first direction `object_tracking_id` : Unique identifier for a specific object, as specified by `object.id` property (see AI Model Node )
`<roi_label>.cur_dir2_objects`	List of object IDs	Information about the objects currently crossing the line in the other direction `object_tracking_id` : Unique identifier for a specific object, as specified by `object.id` property (see AI Model Node )