Setting up VMD-based Scene Analytics detection tools

Attention!

If you plan to use the metadata from the VMD for MomentQuest (see Forensic Search for Fragments (MomentQuest)), you may need to update the license file. Contact an Grundig manager for detailed information and license file.
The Abandoned object detection works only with the basic Object tracker (see Settings specific to Abandoned object detection).
It is not possible to determine the object type and color based on metadata from VMD.

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

Select a Motion detection object.
Select Yes in the Object tracking field.
By default, metadata are not recorded into the database. To enable metadata recording, select Yes from the Record objects tracking list.
For a proper operation of VMD-based Scene Analytics detection tool, it must analyze a frame at least every 500 milliseconds (see Configuring VMD for the Frames processed per second and Decode only key frames parameters description).
Select a processing resource for decoding video streams. 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.
To reduce false alarms rate from a fisheye camera, you must position it properly. For other devices, this parameter is not valid.
Click the Apply button.
Next, you must create and configure the necessary VMD-based detection tools. The configuration procedure is the same as for the basic tracker (see Setting up Tracker-based Scene Analytics detection tools).

Space shortcuts