Documentation for Auto PSIM 1.0.1.

Previous page Configuring the AR-Railway module  Requirements for mounting and configuring cameras for carriage recognition Next page

The image received from video cameras must be sharp, contrast and readable for the correct recognition of carriages and containers license plates.

Requirements for the video camera characteristics:

  1. Use video cameras with high resolution (720p is recommended).
  2. The frame rate from the video camera (FPS) is selected individually and depends on the carriage speed: the faster the carriage goes, the higher the FPS should be, and vice versa. However, the higher the FPS, the greater the CPU load.
  3. It should be possible to set a fixed exposure value (shutter) on a video camera of 1/2000 s or less.
  4. High sensitivity of video cameras (0.01 lx and more).

Licensing requirements based on CPU processing power:

CPU1-core license (FPS)2-core license (FPS)4-core license (FPS)
Intel Core i31-21-41-8
Intel Core i51-21-52-10
Intel Core i71-32-72-14

The optical axis of a video camera must be perpendicular to the plane of the license plate. To simplify the setting, it is recommended to use the varifocal lenses. The focal length variation range should be selected in each case of the system installation.

Image requirements:

  1. The position of a carriage or a container in the frame should be strictly horizontal.
  2. Size of the license plate characters in the image must be from 20 to 80 pixels, i.e. from 4% of the image height.
  3. The geometric distortion by optics ("barrels" and "pincushions") should be reduced.

When configuring video cameras, it is also required:

  1. Focus camera exactly on the container or carriage license plate and disable the auto focus.
  2. It is recommended to disable all video camera smart features. For example, the contrast enhancement mode.

The diagrams of mounting video camera for providing the exact recognition of container license plates are shown in the following figures.

Attention!

The FXVD4 capture card and API are required only when you use analog CCTV cameras.

In the above image, you can see a sample application for the ACCR purposes. In many cases the container codes are damaged, therefore we suggest capturing multiple images from different sides of the container and process them together as an image sequence. To get the most precise reading results, it is recommended to use three container cameras. To provide the optimal conditions for taking an image, use two external white LED illuminator devices. With the help of an additional ANPR camera, a truck, carrying a container, can be identified.

To reduce consumption of the computer resources, use external triggering to capture images only if the container code and the license plate are in a good position.
The inductive loop (other triggering possibilities: laser sensor, microwave sensor, magnetic sensor or infrared barrier) serves as a sensor, which indicates the arrival of the vehicle.
As the vehicle stops at the “STOP” sign, all cameras identify the container code and the license plate of the truck.

The reference image received from the correctly mounted and configured video camera is shown in the following figure.

  • No labels