Skip to main content

Video object detection tracker

The video object detection module tracks objects recognized by using AI models. This data can then be combined in the Fusion Tracker module to get a more complete scene understanding.

Instances

A device is preconfigured with a fixed number of instances of this module.

In general there is one instance of this module for each physical video channel corresponding to each image sensor on the device. There is an exception for multisensor cameras that producer a panorama image that is stitched from several image sensors.

  • Devices with one image sensor will have one tracker instance.
  • Multidirectional cameras will have one tracker instance for each image sensor.
  • Multisensor cameras that produce a panorama image that is stitched together from several image senors will have a one instance of the tracker corresponding to the viewarea of full stitched image.

Function

The video object detection tracker tracks and estimates the both positional and attribute object states for objects in the scene.

Configuration

Privacy mask

Using the video-analytics - v1 API in the camera's privacy masks can be enabled. In the same API it is also possible to configure how data analytics should act on such masks.

The api can be found at:

http://camera-ip/config/web-ui/swagger-ui/?url=/config/discover/apis/video-analytics/v1/openapi.json

Output protocols

This modules output is not directly accessible, for more information, see Computer Vision SDK examples.