The VE352 Engine is designed to detect left or removed items in moderately to less busy indoor environments. Typical deployments include retail facilities where detecting removal of merchandise is desired.
The VE352 engine is designed to work in indoor environments in retail. It will not work well in extremely busy environments. Camera position should be at least 15 feet above the ground, and the camera angle can be flexible, depending on the field of view you wish to capture.
Select Server
> Configuration.
Select a camera from the Devices
branch of the left pane.
In the Analytics Engines
tab, select VE352. By default VE250 is selected, in which case you must
first deselect VE250 (see how
to select analytics for more help).
In the Analytics Configuration
tab, select Intel_VE352 from the
Analytics Engines combo box if
more than one Engine is running on the camera.
By default, the Masks
tab is shown. Leave the default settings for the
Analysis FPS and Analysis
Resolution.
In the Persistence
Mask tab, adjust the yellow mask as required (see how
to configure analytics for more help). Select the Erase
and Draw to radio as required
to draw the mask. The Size slider
adjusts the pen thickness.
In the Perspective
tab, set the perspective for the scene: The red lines must be drawn such
that they represent a length of 5m at their location in the scene. The
Person icon will be sized automatically.
Select the Basic tab to
configure additional settings. Usage:
Left item duration (seconds) |
Specifies how long an object must be left before an alarm will occur. |
Initial background model learn time (seconds) |
Specifies how many seconds will be used to build background model. If environment is not busy, adjust value higher such that the confidence of the software is higher (in determining the background from the foreground). |
Object merge distance (pixels) |
Determines the distance (in pixels) between objects where they will be automatically merged as one object. |
Check for object drop-off |
This enables the software to check for activity around the left or removed item seconds before the alarm occurred (such as a hand reaching in). The pixel value defines the search area around the alarm. |
Reduce false alarms from still people |
May be used to reduce alarms caused by people standing in scene. The seconds value will determine how long to filter out still moving objects. |
Reduce reflection |
Enables another filter which attempts to reduce false alarms caused by reflections. |
Camera looking at shelf |
This should be enabled or disabled depending on camera location relative to shelf. |
9. Click OK to save configuration changes.
Configuring the VE352 (see above) is required before creating a Rule. To configure a Rule using the VE352, follow the steps below:
Mark the alarm zone using the Draw and Erase radio buttons. The Size slider adjusts the pen thickness. Objects that are left or removed outside the red alarm zone will not cause alarms. The VE352 does not distinguish between a left or removed item.
Specify what percentage threshold for an object which is not fully inside an alarm zone by adjusting the Alarm based on percentage of object inside alarm mask option.
Optional: Alarm conditions may be filtered
by enabling the Alarm only, if
or OR, at least options. Both
conditions can be enabled together or separately.
The Alarm Only filter is designed for retailers who wish to only alarm
if a certain number of alarms (or merchandise) is removed from the shelf
in a pre-determined time. For example, 2 LCD monitors must be removed
before the event is triggered. The OR, at least option is a work-around
if multiple objects are removed but they are so close together it creates
one bounding box (and therefore one alarm). Therefore by combining both
filters, many small background changes or one large background change
(caused by a removed item) can trigger the event. Usage summary:
Alarm only, if |
This filter defines how many alarms must occur in predetermined time. |
OR, at least |
This filter defines the size of alarm before |
Alarms Occur |
Filter based on alarms detected |
Pixels Change |
Filter based on pixels changed |
Click Next to continue to next step in wizard.
Currently, there is no distinction between left and removed items.
If objects are too small, detection is difficult. Move camera closer to objects that are to be detected.
See Also