Configuring SharpV analytics - SharpV | SharpOS 13.2

AutoVu™ SharpV Administrator Guide 13.2

Applies to
SharpV | SharpOS 13.2
Last updated
2020-09-16
Content type
Guides
Guides > Administrator guides
Language
English (United States)
Product
SharpOS
SharpV
Version
13.2

You can configure the analytics performed by the SharpV, such as which plates the SharpV will read, and whether the SharpV should attempt to read the plate origin and vehicle make.

Procedure

  1. Log on to the Sharp Portal.
  2. From the Configuration menu, click Analytics > ALPR settings.
  3. From the Context menu, select which license plates will be most commonly read by the SharpV.
    NOTE: For more information on the available regional contexts, see Supported ALPR contexts.
    Tip: To help us improve the performance of regional contexts, click Configuration > Connectivity > Product improvement and register this camera to participate in the Product improvement program.
  4. Under Camera orientation, select the pictograph that describes how the road appears from the camera's perspective. This helps the system to determine the direction that vehicles are traveling.
  5. To ignore parked vehicles, signs, and other static objects, select the Optimize for static image background check box.
    IMPORTANT:
    • Not recommended if only a small part of the image background is static, for example, if many moving trees are visible. This is less likely to happen in installations where the camera is tilted downwards.
    • It is not recommended to use this feature in conjunction with Virtual Loop when vehicles are traveling at speed above 50 km/h (30 MPH).
  6. If a compatible regional context is selected, the Zones field is displayed, which lets you configure the SharpV for single or dual-lane plate reading. For more information, see Configuring the SharpV to monitor dual lanes.
  7. From the Reading mode drop-down list, select one of the following reading modes:
    Continuous
    Select this for plates to be captured continuously. This is the default setting.
    Conditional
    Select this to capture plate reads continuously as long as the selected input signal meets the condition defined (high/low).
    Single read on trigger
    Select this option to force the SharpV to capture a plate read after a signal is received from an electrical trigger, or after a Security Center event-to-action or hot action. This configuration is useful for controlling vehicle access to gated parking lots. You can configure the plate read capture to occur before or after the trigger is activated.
  8. (Optional) If you selected Single read on trigger, click Add trigger and configure the following:
    1. Under Trigger, select when an input (A or B) triggers a plate read based on its state (Low or High). For example, you can specify that Input A triggers a plate read when it transitions to a Low state. You can also select an External input such as a Security Center event-to-action or hot action.
    2. Under Capture window, specify when the SharpV starts capturing (in milliseconds) and whether to do it before or after the trigger. You also need to specify the Duration (in milliseconds) that the SharpV will attempt to capture a plate read.
    3. Under If no plates, indicate how long (in milliseconds) to wait after a trigger before capturing a context image of the vehicle. Select the Use the ALPR image as context image option, when you want an image from the ALPR camera to be used for the no plate read.
      NOTE: Information on context images is not applicable to SharpV ITS cameras.
  9. From the Read strategy list, select a read strategy. The following tables gives general recommendations based on the installation type. For more information, see About Sharp read strategies
  10. Under Analytics, select the contents of the plate you would like the SharpV to attempt to read. You can select the following:
    NOTE: You can add the state, vehicle make, and confidence score as annotation fields in Security Center to query for this information in Security Desk reports.
    State
    Select this option if you want the SharpV unit to attempt read the license plate origin. Depending on the region, this can refer to the issuing state, province, or country.
    Vehicle make
    Select this option if you want the SharpV unit to attempt to read the vehicle’s make from the brand or logo (Honda, Toyota, and so on).
    NOTE: This setting is not recommended for MLPI installations.
    Confidence score
    The SharpV assigns a confidence score percentage to each license plate read. This value indicates how confident the SharpV is in the accuracy of the read.
    NOTE: License plates that contain similar characters such as 8 and B are more difficult to read and generally produce reads with a lower confidence score.
    Vehicle type and color
    Select this option if you want to include the vehicle type and vehicle color with plate reads. Based on the context image, the Sharp unit can detect if the vehicle is a bus, passenger vehicle, motorcycle, pickup, truck, work van, or an unknown vehicle type. In addition, the Sharp unit can detect if the vehicle is black, white, blue, brown, green, gray, orange, red, or yellow. Colors excluding white and black are also assigned light, neutral, or dark according to the color analysis.
  11. If the SharpV is installed at a high angle, it might detect the lettering on the side of passing vehicles and produce false positive reads. Set the Plate tilt filter to ignore text unless it appears at the correct angle in the image.
    NOTE: The plate tilt value is displayed in the Last read section of the Camera feeds page. It is also included as an annotation field which can then be included in read reports.
  12. If the SharpV is installed at a low angle and license plates have a long transit time through the image, you can improve the read rate by setting the Character height filter to ignore license plates until they appear at the right height in the image.
    Tip: The system captures plate reads more accurately if characters are between 25 and 60 pixels high in the images acquired by the ALPR camera. The optimal size of license plate characters is 30 pixels high. You can measure the pixel height on the Configuration > Cameras > Zoom and focus page.
    NOTE:
    • If the SharpV is configured for dual-lane plate reading, the characters must be from 10 to 40 pixels high. For more information, see Configuring the SharpV to monitor dual lanes.
    • The character height is displayed in the Last read section of the Camera feeds page. It is also included as an annotation field which can then be included in read reports.
  13. Click Save.