Skip to content

Line Crossing Detection

Line Crossing Detection is a query type that detects objects crossing a line in a video stream. It can be used to monitor traffic, people, or any other objects crossing a threshold from any or from a specific direction.

Use case examples

Use case Configuration
People entering a restricted area. Draw a line at the entry point of the area.
Vehicles entering or leaving a parking lot. Draw a line at the entrance/exit of the parking lot from the respective directions.
Vehicles going in the wrong direction. Draw a line across the road from the opposing direction.

Prerequisites

Setup

  1. Select a video from your workspace Click +Set up New Query.

  2. Select Line Crossing Detection from the list of query types.

1. Query Name

Give your query a name to better identify it. A description can also be added (optional).

2. Object Detection Filter

Videos

The thumbnail image of the previously chosen video is displayed here.

Time interval

Time interval

Select a time frame for the analytics to run, depending on the type of video selected above:

  • Earliest: Run the query from the time shown (set during video registration as the beginning timestamp of the video).
  • Latest: Run the query until the time shown (set during video registration as the end timestamp of the video).
  • Given Date: You can select a custom start and end date and time to run the query on. Type the desired date and time or select them by clicking the calendar icon.
  • Live: Analysis is run live, continously.
  • Interval: You can select a custom start and end date and time to run the query on. Type the desired date and time or select them by clicking the calendar icon.
  • Set interval to: Choose from the presets below to run the query on a given time interval.

Object types

Select one or multiple object types you want to search for - Person is selected by default. Select a category, then click the dropdown menu to see the list of available object types for the selected object category.

Object types

  • Minimum confidence (0.5 by default): The minimum confidence level required for an object to be detected. The higher the confidence level, the more certain the system is that the object is of the selected type. The confidence level ranges from 0 to 1, with 1 being the highest confidence level.

Add attribute (optional)

Object attributes

Some object types may have additional attributes available for filtering, such as helmet and gender for Person objects. You can select any number of them to further filter your results; For instance, adding the nohelmet attribute to Person objects will filter detections so that only people not wearing helmets will show up in the Query results.

  1. Click the +Attribute button.
  2. Select an attribute from the list.
  3. Tick the checkbox of the respective attribute to toggle filtering - i.e. whether to look for people with helmets or without them.
  4. You can keep adding additional attributes if the object type allows them. Click the X button to remove an attribute.
  • Attribute aggregation type:
    • Logical AND: The query will return results that match all selected attributes.
    • Logical OR: The query will return results that match any of the selected attributes.

Line cross attributes

Linecross

Draw a line on the canvas to define the area where objects crossing the line will be detected. The line can be drawn in any direction, and it will be used to determine whether an object has crossed it.

Left-click on the camera thumbnail to begin drawing the line; left-click again to finish drawing. Select from the options below the canvas to select the facing direction.

  • Ignore duplicate crossings (in milliseconds, 1000 by default): If multiple crossings of the same tracked object occur within the selected amount of time, only one event will be fired for that object. Use this option to avoid counting the same object multiple times, e.g. when a person is walking back and forth across the line.

  • Use bottom reference point: Choose either the center or the bottom of the bounding box as a reference point to determine whether the object is within the ROI.

  • Maximum number of parallel tracks at the same time (50 by default): The maximum number of tracks that can be processed simultaneously. Increasing this number may improve the accuracy of the results but also the processing time.

3. Alarm Integration (optional)

Payload type: DetectionSet.

Results

All done - Clicking Save & Run will immediately start the analysis and opens the Result screen of this query. Alternatively, clicking Save & Exit saves the query without running it.