Documentation for Axxon One 1.0.

Previous page Setting up Neural Tracker-based Scene Analytics detection tools  Examples of configuring neural tracker for solving typical tasks Next page

Video requirements for VMD

To configure Scene Analytics detection tools based on video motion detection, do the following:

  1. Request an updated license file from AxxonSoft manager.
  2. Select a Motion detection object. 

  3. Select Yes in the Object tracking field (1). 
  4. By default, metadata are not recorded into the database. To enable metadata recording, select Yes from the Record objects tracking list (2). 
  5. For a proper operation of VMD-based Scene Analytics detection tool, it must analyze a frame at least every 500 milliseconds (see Configuring VMD section for Frames processed per second (3) and Decode key frames (5) parameters description).
  6. Select a processing resource for decoding video streams (6). When you select an NVIDIA GPU, priority is given to a discrete graphics card (when decoding on NVIDIA NVDEC chips). If there's no appropriate GPU, then decoding will use the Intel Quick Sync Video technology. Otherwise, CPU resources will be used for decoding.

  7. To reduce false alarms rate from a fish-eye camera, you have to position it properly (4). For other devices, this parameter is not valid.

  8. Click the Apply button.

  9. Next, you have to create and configure the necessary VMD-based detection tools. The configuration procedure is the same as for the primary tracker (see Setting up Tracker-based Scene Analytics detection tools).

    Attention!

    VMD-generated metadata does not include object type and color information.

    Attention!

    The abandoned objects detection tool works only with the primary tracker.

  • No labels