Carrida Camera Program User Documentation

Revision: 1.0
Date: 2017-08-30
Contact: alpr.support@vision-components.com
Copyright: 2017 Vision Components GmbH, Germany
Author: VC Support

Table of Contents

1   Introduction

Carrida is a software library for Automated License Plate Recognition (ALPR) in images. The Carrida Camera integrated an imaging and processing device, together with the Carrida 4 engine into a compact embedded license plate reading sensor.

Typical applications of the Carrida Camera include:

  • Parking lot management
  • Vehicle ticketing/management
  • Automatic barrier opening
  • Vehicle counting
  • Law enforcement applications
  • Traffic planning (count vehicles, map traffic to geographic regions)
  • Traffic flow monitoring

Carrida offers the following features and benefits:

  • Easy to configure
  • Any number of license plates per image can be detected
  • Support for State/Country recognition
  • Supports license plates with two rows
  • Supports license plates with stacked characters
  • Robust against illumination, contrast, noise, and rotation

For further details and information see also the related documents:

A list of abbreviations used throughout this document:

ARM
Stands for processors with the ARM instruction set.
ALPR
Automatic License Plate Reader.
dB
Decibel, in the Carrida documents used to describe a relative sensitivity (gain) value in cameras.
FOV
Field of view.
HW
Hardware.
LP
License Plate.
ms
Millisecond, one 1/1000 th of a second.
PC
Personal Computer.
px
Pixel. The smallest unit of resolution in an image. For example, VGA images are made up of 640x480 pixels.
ROI
Region of Interest, typically a marked area in an image.
SDK
Software Development Kit.
SW
Software.
x86
Stands for Processor Architectures with the Intel instruction set.
VC
Vision Components GmbH.
OSD
On-screen display
Image symbols used in this document
Symbol Meaning
Note Sign Points to especially important aspects of the manual or the software.
Hint Sign The Light bulb highlights hints and ideas that may be helpful.
Warning Sign This warning sign alerts of possible pitfalls to avoid. Please pay careful attention to sections marked with this sign.

2   Quick start with Carrida Camera

Enter the configuration page by typing in the address bar of any internet browser (i.e. Chrome, Firefox, Opera etc.) the provided IP address. This will open the Carrida Camera Configuration page.


First two settings categories, Camera and ALPR configuration, contain parameters for adjusting image capturing and image processing. Illustrated on images below are the different OSD layouts in:

  1. Carrida camera configuration,
  2. Camera configuration,
  3. ALPR configuration.
t1 t2 t3

The OSD on the main Carrida camera configuration page will continuously display live image stream. Here image streaming is shown without delay.

Other OSD reproduce video that can be slightly delayed because images are being processed.

On the Configuration page image streaming may be delayed as image processing is taking place.

The green rectangular border on this page represents the brightness control ROI.

Brightness control features will be applied to the area inside this ROI. It is important to resize this area and make it as small as possible to reduce processing time. More about brightness control features and how they affect image acquisition read in Section 4.1.15..

The size of Brightness control ROI should depend on the size and movement of vehicle plates. How to properly determine the region read in Section 4.1.16..


Image streaming on the ALPR configuration page can be slightly delayed. The delay is a result of processing that takes place after image capturing.

The yellow rectangle on the OSD represents the ALPR detection ROI.

Plates outside this border are not going to be considered valid.

When vehicles are not expected to appear in the entire frame resize the ROI. This will shorten processing time as the program will not search the entire frame for plates.

Resize the rectangle by clicking on any of the highlighted corners and drag/drop it to the wanted position. When finished resizing click on ,Apply’ next to the Brightness control region (Camera settings) or ALPR region of interest (ALPR server settings).

What is the difference between the brightness control ROI (green) and the ALPR detection ROI (yellow)?

Brightness control ROI defines the image area within which the camera measures and corrects the image brightness. The polygon should enclose just the area where the vehicle plates will move through the image. It should be as small as possible, but big enough to cover all possible image locations where plates should be detected. How to adjust and use the brightness control settings is explained in Sections 4.1.15.-20..

ALPR detection ROI limits the program to process only the plates within the borders. Vehicle plates outside this area will not be recognized by the ALPR. Limiting it will decrease processing time as the program will not search the entire frame for plates, just the focused area.

The ALPR detection ROI must be bigger and enclose the brightness control ROI.



Before further parameter adjustment notice that two operation modes are included in the GUI, User and Advanced mode. They differentiate in the amount of settings displayed.

  • Mode:User will show commonly used settings. This will give a clearer overview and quick and easy access to frequently used parameters.
  • Mode:Advanced will contain additional camera and ALPR settings which are recommended not to be changed unless necessary (i.e. in case of over saturated images, blurry plates, etc.). By default parameters in Advanced mode are set for optimal performance in most scenarios and are advised not to be changed if not needed.
tt

To switch between User and Advanced mode click on the ,Mode’ button on the upper right corner of the window. For Advanced mode a pop-up window will appear, as shown on the image.

Enter the password and click ,OK’ to access Advanced mode. The password will only be required when switching from User to Advanced mode.

Changing the password is possible under System configuration, see Chapter 8 .

On featured examples User settings will be numerated with blue tags, and Advanced settings with orange tags.

2.1   Start ALPR detection

First thing we recommend is to check if Use brightness control feature is enabled. It is part of Advanced settings, located on the Camera configuration page on the Camera settings card.

Enabling brightness control region will turn on the camera's automatic brightness control feature.

The following parameters are extended features of Brightness control and can be visible only in Advanced mode:

Secondly to reduce processing time, and increase brightness control effect on the images resize the Brightness control ROI.

34

Brightness control ROI is the area enclosed with the green border. All brightness control features will be directed to this area. The ROI are should be defined by the size and movement of vehicles plates through the frame. How to resize this region accordingly is explained in Chapter 2..

Other parameters are set optimally for most situations and it is recommended not to change them. If the images are too dark or too bright than minimum/maximum saturated pixels and brightness low/high can be adjusted to modify image acquisition, see Sections 4.1.17-4.1.20. .


On the ALPR configuration page a yellow rectangle is bordering the OSD. This is the ALPR detection ROI. The program will search for vehicle plates inside the borders.

If vehicles are not expected on the entire frame best practice is to resize the ROI. This will save processing time as the ALPR will be focused on a smaller surface. How to resize this region accordingly read in Chapter 2..

After brightness control ROI and ALPR detection ROI are defined to start image processing and license plate detection enable ALPR Detection. This feature is located on the ALPR configuration page on the ALPR server settings card.


./images_software/CameraSoftwarePic_35.png

By default the programs trigger mode is set to free_run. This means that no triggers are set to start image gathering, and the program will freely detect plates as they appear on the frame.

The performance mode is set to normal, optimized for regular traffic, where processing speed and reading accuracy are balanced.

Under ALPR configuration these and other parameters can be modified for refined plate detection, all detailed in Chapter 5..

If there is a need for access control, it can be enabled on the ACCESS Configuration page. Here lists with vehicle plates, date and time can be created or import. What lists are for, and how to format and import them read in Chapter 6.

2.2   Result images

Two pages display reading results:

  • Result images - will play processed images with overlaid reading results.
  • Text results - results will be listed in table view. Clicking on a list entry will open the processed image with overlaid reading information.

./images_software/CameraSoftwarePic_36.png

The result list can be limited to a certain amount of entries and have a time limitation. On the image above the list is limited to 100 entries or the last 24 hours. When one of those conditions is met the entry will be removed from the list.

Images can be downloaded from the Text result page by clicking on ,Download image’ button on the top right corner.

Overlaid on images are the ALPR reading results. Reading result can consisted of:

  • state of vehicle registration,
  • state recognition certainty,
  • vehicle number plate,
  • number plate recognition certainty,
  • character recognition certainty.
./images_software/CameraSoftwarePic_37.png

Processed image with overlaid reading result.

On the example image above AT stands for the state in which the vehicle is registered, and it is recognized with 68*% certainty. *W554433 are the vehicle number plates, recognized with 100 % certainty. Above each character is the certainty of recognition, in this case 100 %.

How reading results will be formated can be defined on the ALPR Configuration page under ALPR Server Settings, Sections 5.1.3 - 5.1.5. .

3   Carrida Home

After entering the IP address in any web browser Carrida camera configuration page will open. An illustration of the GUI is shown on the image below.

./images_software/CameraSoftwarePic_0.png

Home page of Carrida Camera Configuration

The main part of the page is occupied by the OSD (on-screen display) which reproduces a real time image stream (1).

On the left bottom side (2) of the OSD, the following information is displayed:

  • coordinates of the mouse pointer position on the OSD,
  • RGB scale of a pixel on which the mouse pointer currently fixates.

Show camera information (2) and Show log message (3) buttons are located on the bottom of every screen in the GUI.

They contain summarized information about the program as shown on the example below.

./images_software/CameraSoftwarePic_1.png

Show camera information and Show log message information options.

Camera information will display the serial number of the device, versions of applications running, and used classifiers (marked red).

Classifiers are files which are used to support ALPR. They are sorted by regions and provide additional information about plate specifics, i.e. size of characters, font style, plate dimensions etc. Usage of classifiers significantly improves ALPR. More about classifiers and how to upload them read in Chapter 8.

On the Show log messages tab the user can see logging history during the runtime of the program. The section marked red contains a summarization of current parameter settings. For example the mode chosen is normal, minimum characters to accept is 4, etc. What each parameter means will be explained in the following chapters.

4   Camera Configuration

The essential segment of ALPR is image acquisition (gathering) which can be influenced through parameters in Camera configuration.


Difficulties that may occur during image gathering are the following:
  • poor image resolution, if the plate is too far away,
  • blurry images, can be a result of motion blur,
  • poor lighting and low contrast due to overexposure, reflection or shadows,
  • object obscuring (part of) the plate.

To eliminate these irregularity's it is important to understand how changing settings will influence image acquisition and reflect on image quality.

Camera settings tab allows the user to modify brightness control parameters, and defines gain and shutter speed. How to set these parameters properly and what do they mean read under Section 4.1.

The internal IR LED light can be turned on/of on the LED flash tab, read Section 4.2.

4.1   Camera

Shown on the image below is the Camera configuration screen.

Settings visible only in Advanced mode are numerated with orange labels, and settings visible in User mode are marked blue. The numeration corresponds with the order in which the parameters are explained in the following sections.

./images_software/CameraSoftwarePic_3.png

Camera settings in User mode (marked blue), and Advanced mode (marked orange).

OSD properties are modified with parameters marked on the image above with numbers 1 through 8:

Changing these settings will reflect on the overcast of information on the OSD. An Example how OSD will look like enabling/disabling these features is given after all the parameters are explained, in Section 4.1.8.


Further more, parameters marked on the image above with numbers 10 through 13 directly impact image acquisition. In short, gain represents cameras sensitivity to light, in decibel, and shutter speed measures time, in fractions of a second, cameras sensor is exposed to light from the lens. Change these parameters in case of blurry, un-sharp images. Read more on how Minimum gain (4.1.10.) and Maximum gain (4.1.11.), Minimum shutter (4.1.12.) and Maximum shutter (4.1.12.) effects image gathering in sections 4.1.10. through 4.1.12 .


The fallowing settings (marked on the image from 15 through 20) adjust the brightness of plates. Before changing these parameters we suggest to modify the brightness control region.

What is the brightness control ROI?

Framing the OSD are green lines with yellow rectangles in each corner. The area within this polygon is the brightness control region of interest (ROI). It defines the image area within which the camera measures and corrects the image brightness.

It is important to minimize this surface and limit it to the area only where plates are expected to appear. This maximizes the impacted of brightness control parameters during image acquisition, on the selected area.

How to change this polygon and more information about the ROI find in Section 4.1.16..


When the ROI is defined enable Use Brightness control ( Section 4.1.15. ) to allow brightness control over the ROI . The following parameters will than start taking affect:

If there is a problem of overexposure, or the plates are too dark, than changing these parameters will result in better image quality. Generally we suggest to leave these settings on default values, as they are suitable in most situations. Detail information about how to change the settings with examples are given in continuation of this Section.

4.1.1   Text Prefix

Text prefix is an optional identification name of the camera appointed by the user, i.e. "VC NANO" on sample images in the manual.

If defined it can be displayed on the OSD and Result images. To do that enable Time stamp overlay, Section 4.1.2.

4.1.2   Time stamp Overlay

Time stamp by default consists of information about the date, time and the optional identification name of the camera ( 4.1.1. Text prefix ).

If you enable this parameter the time stamp (and text prefix) will be overlaid on result images and OSD on the top right corner.

Time stamps can be optionally formatted, how to do that read in Section 4.1.7..

4.1.3   Display Shutter

If you enable this parameter the average shutter speed (in milliseconds) will be overlaid on the OSD.

4.1.4   Display Gain

If you enable this parameter the information of average gain (in decibel) will be overlaid on the OSD.

4.1.5   Display camera frame rate

Frame rate refers to the number of individual frames (images) that are displayed in a video per second (fps).

Enabled this parameter allows the information about cameras processing frame rate speed to be displayed on the OSD.

4.1.6   Gain/Shutter position

This parameter effects the position of displayed gain (4.1.3.) and shutter (4.1.4.) information on the OSD. It defines the distance from the top of the image in pixels.

4.1.7   Time stamp Format

A timestamp is a sequence of characters or encoded information identifying when an event occurred.

By default it consists of date and time information formated with following symbols:

%Y-year, %d-day, %m-month, %H-hour , %M-minute , %S-second , %f-millisecond.

A full table with directives which can be embedded in format strings can be found in Chapter 12.

Example:
  • Formatting: %Y-%d-%m %H:%M:%S.%f where the date is separated with "-" and time with ":". Output result: "2017-03-06 15:17:25.455".
  • Examples on how it looks like on the OSD:

ts

4.1.8   Time stamp Size

This parameter will resize Time stamp (4.1.2.), Gain (4.1.3.) and Shutter (4.1.4.) information displayed on the OSD. This change will also reflect on the size of the time stamp on result images.

Enter the new size between 0.0 and 4.0 and click ,Apply’ for the changes to take place.




Example:

The image illustrates how enabling/disabling certain parameters affect the overlay of information on the OSD.

Figure 1: Timestamp, shutter, gain and camera framerate information is displayed on the OSD.

Figure 2: Timestamp overlay and Display gain are enabled, therefore gain and timestamp information is displayed on the OSD.

Figure 3. Shutter and Camera framerate information will be displayed on the OSD.

ex

4.1.9   JPEG Compression Level

JPEG compression reduces the size of images. That results in faster ftp uploads and reduces bandwidth consumption.

Compression level can be set on the scale from 1 to 100%, and the higher the rate produces images lower in quality.

Our recommendation is to set the level on 65%, as best compromise between the quality and size.

4.1.10   Minimum Gain (dB)

Gain controls the amplification of the signal from the cameras sensor. It boosts the signal by some amount thereby making already captured images look brighter.

As a result of signal enhancement negative image blur may occur. The reason is that the overall signal is boosted, making also noise more visible.

Our recommendation is to set this parameter to 0.

4.1.11   Maximum Gain (dB)

Gain controls the amplification of the signal from the cameras sensor. It boosts the signal by some amount thereby making already captured images look brighter.

As a result of signal enhancement negative image blur may occur. The reason is that the overall signal is boosted, making also noise more visible.

Reasonable upper limits are typically 6-10 db. We recommend a maximum gain value of 10 for the Carrida Camera.




What is a shutter?

Cameras shutter is a mechanism that lets in light through the lens onto the cameras sensor. It has two states-open and closed, and the time it stays open is measured in fractions of a second.

Fast shutter speed means the shutter will opens and closes quickly, therefor only a small fraction of light passes through. Slow shutter speed means that it stays longer open, which allows more light to pass through, producing brighter images.

Closing the shutter in fractions of a second gives control over motion blur. What that means is if the shutter closes faster in the relation to the object capturing the result image will be sharper. Vise versa, if shutter speed is slower than the object on the image, images may be blurred.

In further text read how to set minimal exposure(shutter) speed (4.1.12.) and maximal exposure(shutter) speed (4.1.13.) accordingly to vehicle speed. Setting this parameters will give the ALPR SW a range (in microseconds) in which the exposure time can vary.

4.1.12   Minimum Shutter

Minimum shutter refers to minimal exposure time in microseconds that the shutter will stay open.

Shutter speed should be changed according to vehicle speed. If the vehicle is approaching in high speed, the exposure time should be reduced.

When minimum shutter is set too high (in relation to the vehicle speed) it may cause lower reading performance because images can turn out blurry.

As a general recommendation, the following exposure (shutter) times are advised:

  • shutter time of 0.1-3 ms on highways, for high speed vehicles
  • shutter time of 0.1-3 ms in urban areas, for medium speed vehicles
  • shutter time of 1-20 ms in parking situations, for slow vehicles
What to do if vehicles are blurry?
  • In that case the shutter speed might be set too high. Try reducing it according to recommended exposure times on the list above.

4.1.13   Maximum Shutter

Maximum shutter refers to maximal exposure time (in microseconds) that the shutter will stay open.

It is recommended to set this parameter higher during lower light exposure. It will raise the visibility of the plates, as more light will come trough the lens. This does not mean the higher the shutter is set, the better. In the same scenario when a car is in higher speed it will cause distorted images.

How to estimate the maximum allowed exposure time:

The maximum possible exposure time can be calculated from the viewing geometry and image resolution. The basic principle is that a vehicle should not move more than 1 px in the image during exposure time, at maximum possible speed.

It is possible to either compute this value exactly using measurements of the visible street section, viewing angles, etc. or it can be approximated. By measuring the time (T) it takes a vehicle from top to bottom,or left to right of an image - whatever time is shorter - and the image resolution in this direction (i.e. number of pixels), the maximum allowed exposure time in ms can be computed as follows: exposureTime(ms) = 1000*(T/resolution)

A general recommendation how to set exposure time can be found in Section 4.1.12. .

4.1.14   Low Resolution

Carrida camera sensor can operate in two resolutions, low resolution 640x480 pixels and high resolution, 1280x960 pixels.

If Low resolution is enabled images will be captured in 640x480 pixel resolution. If it is disabled high resolution will be activated.

Hint

Hint Sign Enabling low resolution has the advantage that the achievable frame rate becomes higher because less data has to be transferred to memory, and thus less processing is necessary.

4.1.15   Use Brightness control

Use Brightness control allows brightness control over the defined region of interest (ROI). What is the brightness control ROI read in the next section, 4.1.16.

Our recommendation is to leave this parameter enabled at all time as it will enhance image quality, and produce better ALPR results through following settings:

These parameters are by default set to suit most indoor/outdoor situations and are recommended not to be changed if not necessary.

4.1.16   Brightness control Region

Brightness control region, also called the brightness control ROI represents a polygon and encloses the ROI which will be affected with brightness control parameters. Looking at the image below it is visualized as a green polygon with yellow corners.

It is important to limit the region within the polygon only to the area where the plates will move through the screen. Making the ROI as small as possible, but big enough to cover the movement of the plates trough the screen, will maximize the affects of brightness control parameters (see Sections 4.1.17-4.1.20.) .

Resizing the Brightness control polygon  
Click, drag and release the yellow corner. Click on 'Apply' next to Brightness control region option on the right side menu to save changes. region
Example:

Select the area where you expect the vehicle plates, like show on the image below.

./images_software/CameraSoftwarePic_7.png

In this case the camera is mounted in front of the gate. The polygon captures all of the whole path on which the vehicle will appear on the screen. This will direct parameters for brightness control to affect a more specific area, therefore producing clearer images with less processing time.

4.1.17   Brightness control maximum saturated pixels

Exposure control of the camera counts all good pixels within the Brightness control ROI. Good pixels are those, which are not too dark or too overexposed. The limits are defined with the Brightness control brightness low and Brightness control brightness high and should generally not be modified.

A pixel is saturated when it takes on its maximal value, in this case the value set in Brightness control brightness high . When pixels are saturated they loose information about the scene.

In case where there are too many overexposed pixels, the camera will change its exposure settings to make the image darker. The correct pixel counts are indicated as percentage (0-100) relative to the image size.

Hint

Hint Sign What to do if the license plates are always overexposed?

If the license plates are constantly to bright, the percentage value of maximum saturated pixels needs to be reduced, so that the camera tries to reduce the count of those pixels. Example: reduce the value from 5 to 3 % and observe the effect in the live image.

4.1.18   Brightness control minimum correct pixels

All pixels with lower brightness than set in Brightness control brightness low will be considered as not enough illuminated pixels. All pixels with higher brightness value than set in Brightness control brightness high are considered overexposed. Pixels that are between low and high brightness levels are considered well lighted/correct pixels.

Correct pixel count is indicated as percentage (0-100) relative to the image size. If there are to many overexposed and underexposed pixels the camera will adjust exposure settings to get the correct pixel amount to reach at least the minimal level set here.

Hint

Hint Sign What to do if the license plates are always too dark?

If the license plates are constantly to dark, the value of minimum correct pixels needs to be increased, so that the camera tries to increase the number of those pixels. Example: modify the value from 3 to 5 % and observe the effect in the live image.

4.1.19   Brightness control brightness low

You can set the lowest brightness threshold between 0-255 pixels. All pixels with lower brightness will be considered as not enough illuminated. By default the value is set to 100 pixels and we recommend not to change it.

4.1.20   Brightness control brightness high

You can set the upper brightness threshold between 0-255 pixels. All pixels with higher brightness will be considered as over illuminated pixels. By default the value is set to 220 pixels and we recommend not to change it.

Note

Note Sign It is recommended not to modify the following parameters:

  • Brightness control brightness high
  • Brightness control brightness low.

4.2   LED Flash

Carrida camera is equipped with infrared (IR) LED flash. It produces artificial light to illuminate vehicles.

On this tab `Flash duration` and `Flash current` can be altered.

Flash duration is measured in fractions of a second, and measures the time the flash is emitting light. By default it is set to 300 milliseconds and our recommendation is not to change this as it will be applicable in most scenarios.

The second parameter that can be set for LED Flash lights is the Flash current. It is expressed in milliAmpers and should be left on default value of 200 mA.

./images_software/CameraSoftwarePic_8.png

LED Flash settings on the Configuration screen.

4.2.1   Enable Flash

Carrida camera IR LED lights produce artificial light to illuminate vehicles. Enabling flash will turn on the Carrida cameras IR LED lights.

We recommend to leave flash enabled at all time.

4.2.2   Flash Duration

Flash duration measures the burst of light which creates the exposure. It measures the duration when the flash is actually on, emitting light.

As the duration gets shorter it has a better ability to obtain control over motion. For example shorter flash durations are desirable when dealing with vehicles that are moving faster.

4.2.3   Flash Current

Carrida camera IR LED lights produce artificial light to illuminate vehicles.

The controller covers a current range from 150 to 1500 mA. We highly recommend to leave the current set to 200 mA. If the duration is set to values 150 mA or lower the flash will be turned off.

The FLASH0and FLASH1outputs are available over the Power Connector J0. The VC pro Z Hardware features four independently adjustable current sources for the connection of four LED light sources. Specific information about the connectors and other technical data can be found in the VC pro Z Series Operating Manual .

5   ALPR Configuration

On the ALPR configuration tab setting for the fallowing features can be altered:

  • ALPR Server
  • Trigger
  • ALPR Parking mode and
  • ALPR Engine.

On the ALPR Configuration screen framing the OSD is a yellow rectangle with green corners. This is the ALPR region of interest. The SW will read plates only within these borders. More information about this region is provided in Section 5.1.7.

To start image processing enable 'ALPR Detection' (Section 5.1.1.) on the `ALPR Server settings` tab. This will initialize ALPR SW to start processing and producing result images.

In the continuation of this chapter all settings that appear on the `ALPR Configuration` screen will be in detail described. Featured images will have blue number tags for settings visible in User mode, and orange number tags for settings visible in Advanced mode.

5.1   ALPR server settings

The set of parameters under ALPR server settings tab allow to configure how the result image plates will be visualized, resize the ALPR region of interest, and initialize ALPR detection.

The first parameter, ALPR Detection, needs to be enabled for the ALPR SW to start processing and recording results. The results will than be displayed in table view under Text Results.

Visual properties of ALPR result images can be modified through the fallowing parameters (on the image marked from 3-5):

Enabling/disabling any of these options will reflect on the design of result license plate images, as shown in Example 2. , Section 5.1.5.

./images_software/CameraSoftwarePic_9.png

Here the term ALPR region of interest (ROI) is introduced. This is the area within the yellow rectangle. The purpose of this area is to limit ALPR detection only on vehicles within those borders.

5.1.1   ALPR Detection

If ALPR detection is disabled the program will not record or process any license plates.

Enabled ALPR plate detection and processing will start. All results will be listed in Text Results,.

5.1.2   Result Buffer Size

Result buffer represents a temporary storage for processed images. It has the capacity to save up to 20 images.

The images are stored internally until they are collected by the program. When the buffer is filled up, older entries are dismissed and replaced by new results.

5.1.3   Display Plate

When enabled, ALPR will generate an image of the read plate and overlay it on the processed images (see Example 2.).

5.1.4   Display State

If display state is enabled state name with the percentage of reading confidence will be overlaid onto processed images.

This parameter will be activated only in combination with display plate. If display plate (5.1.3.) is not enabled state information will also not be displayed.

Example:

Enable display plate and display state.

A vehicle with number plates W554433 was detected.

As a reading result the SW will overlay "AT 68 W554433 100" onto the result image. "AT 68%" AT stands for Austria, the state, and 68% is the percentage of recognition confidence for the state. "100" stands for 100% certainty that the plate read is "W554433"(see Example 2.).


State/country recognition is possible when appropriate classifiers are in use. Classifiers will be included when initializing ALPR. In case there is need for additional classifier packages they can be uploaded through `System Configuration-Upload classifier`.

5.1.5   Display character confidence

Enabling Visualize character confidence, confidence of recognition for each character will be overlaid above the vehicles number plates.



Shown in the table below are examples of overlaying plate, state and character confidence.

Example:

Image (A) displays a result plate image with visualization of state and plates enabled.

On the image (B) plate, state and character confidence visualization enabled.

Image (C) is generated only with plate visualization enabled.

vz

5.1.6   Display reading frame rate

Frame rate refers to the number of individual frames (images) that are displayed in a video per second (fps).

If Display reading frame rate is turned on (enabled), the reading frame rate will be displayed on the upper right side of the image stream.

5.1.7   ALPR Region of Interest (x, y, width, height)

On the OSD a yellow rectangle frames the image, illustrated on the image below. The area inside the rectangle is the ALPR ROI where processing takes place. Meaning, the ALPR engine will search for plates only within the ROI borders.

./images_software/CameraSoftwarePic_33.png

ALPR region of interest (ROI) specifies the reading area for ALPR recognition.

The rectangle can be re-sized with "click and drag" method, selecting one of two green marked corners. When done with resizing click 'Apply' on the right side menu, next to the 'ALPR region of interest' field for changes to be saved.

Resizing will not improve the readout rate from the sensor, but nevertheless achieves a higher processing rate because the ALPR software needs to process fewer pixels.

5.1.8   Hash Result

MD5 hash is widely used to provide assurance that transferred files arrived intact.

Enabling hash result an MD5 hash will be added on the license plate before transmitting it to the program thereby checking data integrity against unintentional corruption.

5.2   Trigger

Triggers can be used to start/stop image gathering. Carrida camera offers four different trigger modes, described in Section 5.2.1.:

  • Free_run
  • Start_Stop
  • Start_Time
  • Start_Freerun

If there are no triggers defined the ALPR should be set to Free_run mode. It will than freely grab images when plates are detected and start processing.

./images_software/CameraSoftwarePic_11.png

Other modes will depend on certain digital inputs to start/stop collecting images. These inputs are defined with Start trigger line and Stop trigger line parameters. Assign one pin for each parameter which will be set as start/stop trigger, see Sections 5.2.2. and 5.2.4. for more information.

5.2.1   Trigger mode

A reading cycle describes a time period during which ALPR attempts to capture number plates. Image grabbing/collection refers to the event when the ALPR recognizes a new number plate and forwards it to processing.

Trigger modes differentiate in actions that start and stop the reading cycle. A cycle can be ended by a timeout, new start trigger, or a stop trigger.

If there is no need for trigger usage leave the mode in free_run and ALPR will always be operating in image collection mode.

There are two basic types of polarity sensitivity and two sorts of polarity items: negative polarity, it occurs only where it s allowed by the polarity trigger, and positive polarity items, they occur only in contexts when they are not blocked by a polarity trigger.

Negative polarity items can be thought of as dependent because their use depends on the availability of a suitable trigger. On the other hand, positive polarity items are not dependent because their use requires the absence of some class of trigger.

  Mode Description Usage
tm Free_run ALPR detects plates automatically when vehicles appear, processes them and produces output results. This should be the default mode when external trigger is unavailable.
Start_Time Image grabbing starts when a certain trigger is activated, and stops after some time (set in Trigger Timeout) passes, the image is processed and result created. If a new start trigger is detected before the set time passes, the previous session will be closed, image processed, and a new image grabbing cycle will start. Trigger timeout ends the reading cycle. Result of this reading can be a plate image sent to be processed, or No Read event, if no vehicles were detected. This mode is time dependent. Set this mode when the maximum length of time between vehicles can be predicted.
Start_Stop Image grabbing will start when start trigger is activated, and stop when the stop trigger is activated. If a new start trigger is detected before receiving a stop trigger for the previous session, the cycle will be restarted, new image grabbing process will start and new results created. When vehicles move past the camera in irregular intervals. A stop trigger will end the past reading cycle.
Start_Free-run Image grabbing will start when start trigger is received, there is no stop trigger, the ALPR continues working in free run collecting images as new vehicles appear. Used when a specific event should start image grabbing and no stop trigger is to be defined.

5.2.2   Start Trigger Line

Define a starting trigger trough input pins. There are 32 pins available, from 0 to 31.

When this pin is activated/triggered it will send a signal to the camera to start the reading cycle.

An overview of active input and output pins can be found under `System configuration-System information`

5.2.3   Start Trigger Polarity High

Allows the user to turn on start trigger polarity high. That means that the high state will be the active state.

By default this parameter is set to true (enabled).

5.2.4   Stop Trigger Line

Define a stop trigger trough input pins. There are 32 pins available, from 0 to 31.

When this pin is activated/triggered it will send a signal to the camera to end the reading cycle.

An overview of active input and output pins can be found under `System configuration-System information`

5.2.5   Stop Trigger Polarity High

Allows the user to turn on stop trigger polarity high. That means that the high state will be the active state.

By default this parameter is set to true (enabled).

5.2.6   Trigger Timeout

Trigger Timeout measures the delay period (in milliseconds) between the Start and Stop triggers.

If a new start trigger signal occurs before the Trigger timeout passes, the time period will be reset.

If set to 0 there is no delay.

5.3   ALPR Parking mode

The Carrida camera can be configured so that it either transmits every reading result directly to a client, or to a connected application. In many situations this behavior is undesirable, because only one good result is sufficient.

The camera can be configured in a way that only a filtered, verified reading will be transmitted, and only when a new license plate enters the field of view, a new transmission is started. This is called parking mode.

./images_software/CameraSoftwarePic_13.png

ALPR Parking mode menu in Advanced mode.

These set of parameters are only visible in advanced mode as it is not meant to be changed often.

Some parameters delay the output of images and readings, which may be undesirable in some situations. In the continuation of this section read more how and when to change settings in parking mode.

5.3.1   Minimum Detections

Minimum Detections control how many readings of the same license plate will be made until a definite result is produced. Only after this number of readings the transmission of a result will take place.

A new reading is accepted as valid if:

  • it has the minimum confidence defined with parameter Min Plate Confidence, section 5.4.8..
  • The number of character differences to previously read strings is not greater than Maximum Plate Mismatch, section 5.3.6..
  • The location of the license plate is not less than Horizontal (section 5.3.4. ) and Vertical border (section 5.3.5. ) from the ALPR region of interest (section 5.1.7. ), the image area within which readings take place.
  • Less than Drop After (section 5.3.3. ) readings have occurred since the last valid reading.

Note

Hint Sign Minimum Detections will delay the transmission of images and readings.

5.3.2   Buffer size

The camera has a configurable internal image buffer which holds ALPR results. In case ALPR is not able to retrieve images at the same rate as they are produced this buffer can temporarily store those images. It has a ring structure, meaning that the oldest entries will be overwritten if it is filled up.

Buffer size delays readings by the number of images captured multiplied with the cycle time of approximately 300 ms, smoothing out reading errors, which have been compensated (like missing characters).

If Live Image Mode (????) is turned off, the buffer is only filled with valid license plate reading results. In this case the buffer size should be set to 1.

The buffer fills up with images to supply a continuous image stream, even if no license plates are found. In that case a buffer greater than 1 is be preferable.

We recommend to set the buffer size to 1 when monitoring access control. Setting the size greater than 1 is useful when dealing with video processing and visualization.

Note

Hint Sign A buffer size > 1 delays the output of images and readings. A delay of reading results is approximately 300 ms * Buffer Size. For some access control scenarios this can come across as undesired.

5.3.3   Drop after

Drop after defines a number of empty images or new readings after which new license plate will be produced. If it is set to a higher value negative effects of interruptions during reading are reduced, i.e. people walking in front of the license plate.

The value of this parameter can be converted into time by multiplying it with the camera cycle time of 300 ms. If the Drop after is set to 4, multiplied by 300 ms results in a delay of 1.2 sec.

Example:

Readings for the last seven successive frames: ABC123 x ABC123 x x x ABC123 (x being a frame without reading results).

If DropSize = 5, single result will be produced. But if e.g. DropSize = 2, two reading results will be produced, as there is a gap of three frames without reading results.

5.3.4   Horizontal Border

This parameter refers to the distance from the left/right side of the ALPR ROI to the vehicle number plate.

Horizontal border is set in percentage from 0.0 to 10.0. This value can be converted into pixels by multiplying the Horizontal border with the average height of detected plates. ALPR will than ignore plates which appear closer to horizontal sides of the ROI than defined.

This avoids reading incomplete number plates, when vehicles can appear partly in frame. Those plates are than dismissed as being to close to the border.

Example:
Horizontal border is set to 3.0, and the plates appear in e.g. average size of 25 pixels, the license plate must have a minimum distance to the left or right side of ROI 3x25=75 pixels. See example image in section 5.3.5.

5.3.5   Vertical Border

This parameter refers to the range from the top/bottom side of the ALPR ROI to the vehicle number plate.

Vertical border is set in percentage from 0.0 to 10.0. The value can than be converted into pixels by multiplying the Vertical border with the average height of detected plates. ALPR will than ignore plates which appear closer to vertical sides of the ROI than defined.

This setting avoids reading incomplete number plates, when vehicles can appear partly in frame. Those plates are than dismissed as being to close to the border.

Example:
Vertical border is set to 3.0, and the plates appear in average e.g. size of 25 pixels, the license plate must have a minimum distance to top or bottom sides of ROI 3x25=75 pixels.
./images_software/CameraSoftwarePic_41.png

On the image vertical and horizontal border limitations are illustrated with a white rectangle. This rectangle will not be displayed on the OSD, it is used in this example for better visualization and understanding.

Image A shows vehicle plates outside the horizontal border, too close to the ALPR ROI. These plates will not be recognized until they are not fully visible, image B.

Our recommendation is to set both parameters to 1.0, this will eliminate the possibility of reading incomplete plates.

5.3.6   Maximum plate mismatch

Maximum plate mismatch refers to the maximum amount of characters allowed to be different between two plate strings for them to merge.

Recommended to be set to 1.

5.4   ALPR Engine settings

The ALPR Engine Settings control the actual reading of license plates.

There are four different modes in which the ALPR engine operates:

  • Free flow
  • Fast
  • Normal and
  • Best

They differentiate by processing speed and accuracy (Section 5.4.1.).

Under ALPR Engine Settings the search can by refined setting the character size, style (number of characters, inverted color plates) or character confidence, and other parameters explained in the following sections, illustrated on the picture below with numbers 2 through 11.

./images_software/CameraSoftwarePic_14.png

ALPR Engine settings in Advanced mode.

5.4.1   ALPR engine mode

The Carrida engine can operate in several performance modes, which are differentiated by recognition speed and reading accuracy.

Free flow means that vehicles are moving without specific restrictions, open traffic.

Controlled access refers to situations where vehicles are forced to go through a gate at low speed, or need to stop in front of a barrier.

In the table below fast, normal, best and free flow mode are described.

  Mode Description
mo Freeflow Fastest possible processing speed with lower recognition quality as in other modes. Recommended for open traffic when recognition speed has priority.
Fast Fast processing speed with slightly better recognition quality than in freeflow. Also intended for open traffic situations.
Normal A good compromise between speed and reading performance, recommended to be used in most situations. This mode will give best results for open traffic situations with processing speed slightly lower than in previous modes.
Best The best possible reading quality. Can be up to two times slower than in the fast mode. At the same time, reading confidence will be about 3-4% better.

5.4.2   Minimum letter height

Set the minimal height of characters, in pixels. The ALPR will only accept characters larger in size than set in this parameter.

The value should not be less than 8 pixels.

Characters that are smaller in size defined in minimal letter height will not be recognized by the ALPR.

5.4.3   Maximum letter height

Set the maximal height of characters, in pixels, that ALPR will acknowledge.

All characters bigger than the given size will not be processed and will be dismissed by the engine.

We recommend to set this value to 40 pixels.

5.4.4   Maximal plate angel

If vehicles can appear on images under a certain angle to the camera, ALPR can be instructed to search for plates in a wider angle relative to x-Axis.

The angle can be set between 0 and 90°, but best results are recognized between 5° and 30°.

5.4.5   Minimum characters to accept

This parameter refers to the lowest number of characters (letters and numbers) on the license plate that the SW recognizes.

License plates with a character count smaller than set in this parameter will be ignored.

5.4.6   Maximum characters to accept

This parameter refers to the highest number of characters (letters and numbers) on the license plate that ALPR will accept as valid. You can set the upper limit of characters up to 20.

License plates with a character count larger than set in this parameter will be ignored by the ALPR.

5.4.7   Minimal character confidence

Minimal character confidence level is the lowest accuracy level for each symbol on the plate to be accepted as valid by the recognition software. The range is from 0 to 100 percent (%).

If, for example, ALPR reads a character with confidence level 54%, and Minimum character confidence is set to 60%, ALPR will consider this character invalid and will not include it in the result reading.

./images_software/CameraSoftwarePic_43.png

How minimal character confidence influences ALPR results.

5.4.8   Minimal plate confidence

Minimum plate confidence refers to the minimum confidence level at which the ALPR will recognize a license plate as valid. Range varies between 0 and 100 percent.

If minimal plate confidence is set to 70% the program will produce only results with the level of recognition certainty 70% or above. All lower readings will be ignored.

5.4.9   Scale Height/Width

When this parameters are adjusted, the input image will be modified by the given ratios before processing starts.

The re-sizing values have to be provided in percent of the original size (100 = original size).

5.4.10   Search inverted

When search inverted is disabled ALPR recognizes plates with light colored background and dark colored characters (i.e. black symbols on white background).

If this search is enabled inverted plates will be also searched for. ALPR will in addition to regular black-on-white plates look also for white-on-black plates.

./images_software/CameraSoftwarePic_44.png

Example of inverted and regular plates.

Note

Warning Sign Enabling inverted search will increase processing time per image.

6   ACCESS Configuration

ACCESS configuration provides control and an overview of vehicle access (i.e. gate control).

For configuring access control certain actions can be defined. These actions can be preformed when a specific plate number is detected, or it can be configured for every reading.

Detections of specific plates are based on lists. Users form these lists as textual documents with the following information: number plates, date(s) and time. How to format them properly read in Section 6.1..

A list can be created directly on the configuration page (1), entering the plate information in the yellow text box, or they can be imported. For the ALPR to acknowledge formed lists make sure they are uploaded.

The lists can be appoint to four different document classes: ignore, white, black, and permanent (2).

./images_software/CameraSoftwarePic_16_a.png

Access control configuration page.

Marked with numbers 3 and 4 on the image above are actions which can be initialized in case of positive or negative matches. Most common actions are ftp uploads, where images can be uploaded to specified host(s), or ftp database where a cvs file is created and/or updated. Other possible actions are store, digital out, notification, serial and transmission control protocol described in Section 6.2. .

Before setting up the lists and defining the actions access control (5) for ALPR needs to be enabled. Only than will the interface show the list options.

An additional preference to set up is the gate detector. The gate detector is initialized using a trigger. How to set it up read in Section 6.4. .

6.1   ACCESS lists

Lists are text documents used to trigger actions when a plate from the list is detected. For example plate information with an image file can be sent to the ftp server, a signal can be sent for gate control, csv file can be updated, etc.

Form a list combining up to 3 parameters:

  • plate number,
  • date and
  • time.

Plate number is a stand alone parameter, and can be written in combination with a date (or multiple dates), or with date and time. Time needs to be defined with specific date(s). Setting time without a corresponding date will be an invalid entry.


There are two ways to form access lists: importing or creating it directly on the ACCESS configuration page.


How to import a list?

Open any text editor to create a file and save it any_name.txt. Only textual documents can be imported.

Enter information according to the formatting rules and save the file. On the ACCESS configuraton page click on ,Import’ and select the newly created document from your device.

If importing was successful the content from the document will display on the screen. This list can here be edited if needed.

When the list is finished click on ,Upload’ to submit. After uploading the ALPR will register the information and implement the list.


Formatting rules:
  • Do not use blank spaces, everything should be written in a single line.
  • Plate number, date and time must be separated with semicolons (;).
  • When listing multiple dates/times separate them with commas (,).
  • Date format is: YYYYMMDD-YYYYMMDD, with no space between the numbers.
  • Time format is: HH:MM-HH:MM. Time is always defined in combination with a date and a symbol (0/1) for the referred day of the week.
  • Days of the week are represented with zeros and ones (0-not active, 1-active) written inside brackets starting with Sunday, ending with Saturday (0111110). In example "0111110" non-active days are Sunday and Saturday, represented with zeros (0).
  • The amount of dates set must be equal to the amount of time restrictions ( W223344;20170101-20170101,20170102-20170102,20170103-20170103;03:00-04:00(0111110),03:00-04:00(0111110),03:00-04:00(0111110) ). If there are more dates than time restrictions (and vice versa) the command will be perceived as invalid.


Practical examples and descriptions of the rules are shown in the table below.

  Example Description
Only plate number W223344 Actions will be taken when a vehicle with this plate number is detected.
Plat number and date   Date format:YYYYMMDD-YYYYMMDD, no blanks.
W223344;20170925-20170925 Actions will be taken if the plate is detected on a date inside set limitations ( 20170926<=[current date]<=20170925).
W223344;20170925-20170926,...,20170529-20170629 Multiple dates can be set,separated by a comma defined in one line, without blanks.
Plate number, date and time   Time format: HH:MM-HH:MM(0111110); 1 and 0 represent days of the week, starting from Sunday(0) till the last day Saturday(0), 0 meaning not active, 1 meaning active.
W223344;20170925-20170925;03:00-04:00(0111110) Time must be set in combination with date.
W23344;20170925-20170925,201701012-20171112,...;03:00-04:00(0111110),05:00-06:00(0111110 ),...

When there are multiple dates, if time is set for one date it must be defined for all the dates or the limitation will be found invalid.

In this example two dates with according times are set where date(1) 20170925-20170925 is combined with time(1) 03:00-04:00, and date(2) 20170112-20171112 is combined with time(2) 05:00-06:00 and so on.

     
Example: W223344;20170101-20170125;03:00-04:00(0111110) an action will be taken if the vehicle with plate number W223344 is detected from 01.01.2017 (00:00) until 25.01.2017 (23:59) between 03:00 and 04:00 on any day of the week, except Saturday and Sunday (0111110).

On the figure below is an imported list with four different entries:

  • Only license plates. An action can be executed every time this vehicle is detected.
  • License plates with two dates, 05.05.2017-25.05.2017, and 05.05.2017-25.05.2017. An action can be executed if the vehicle is detected between the given dates.
  • Third entry is the combination of license plates, date and time. An action can be executed for example if the vehicle is detected between 05.05.2017-25.05.2017, in the time period between 3:00 and 4:00, on all days of the week except Saturday and Sunday.
  • The last entry is the same combination as the previous, with all limitations, but with multiple dates and time periods.
./images_software/CameraSoftwarePic_38_b.png

Formatted and imported ACCESS list.


To trigger actions when any plate is detected upload a combination of symbols !* to a list class (i.e. permanent list).

Example:
If " !* " is on the permanent.txt list, and for this list a positive matching action 'Store' is enabled, the program will store all detected plates. pc

6.2   Positive/Negative Matching Actions Add...

For every list formed (ignore.txt, black.txt, etc.) actions can be added.

x

There are two triggers for actions: positive or negative matches. To add an action click on 'ADD', and make a selection from the list that appears.

To remove an action, simply mark it and click on 'Remove'.

When clicking on the selected actions (i.e. ftp upload) the list of related parameters will become visible. Different actions offer different set of parameters individually explained in the flowing sections.


Some actions will have a field to define a naming pattern.

Naming patterns are used to specify which name should ALPR generate with the reading result. They can be constructed using placeholders for specific information and regular text.

Placeholders are characters written between two percentage (%) symbols (look at the example below). They are later substituted with specific information about a reading.

Example:

A placeholder for license plate is %LP%, for the date is %DAY% %MONTH% %YEAR%, level of confidence for plate recognition is %CONF%. The ALPR detected a vehicle with number plate W223344 on the 03.08.2017, with a level of confidence 98%. The following naming patterns can be formed

  • Naming pattern: Detected %LP% on %DAY% / %MONTH% / %YEAR% .
  • Output: Detected W223344 on 03 / 08 / 2017 .
  • Naming pattern: %LP%(%CONF%) on %DAY%/%MONTH%/%YEAR%.
  • Output: W223344(98) on 03/08/2017.

A complete list of placeholders can be found in Chapter 11 .

6.2.1   Ftp Upload

3

Ftp upload is most commonly used action. It can save image files of detected plates to a remote ftp server.

Set Enable to true for the action to be executed (as shown on the image) .

Enter the Host ftp servers IP address.

Username and Password of the ftp server must be written in the form of: [username]:[password]. Example: for the user name "user123" with the password "pass123" the correct form is: user123:pass123 .

Naming patterns are used to include specific reading information (date, time, plate...) in the file name. How to use and format names using patterns read in Chapter 11.

Images can be uploaded as following:

  • 0 : Empty file
  • 1 : Full image
  • 2 : License plate image only

Empty file sends files with no images. This saves memory and increases the upload speed.

Image quality refers to the compression rate, it can be set from 1 to 100%, 1 being the maximal compression level which will produce images with the lowest quality, and 99 being the minimal compression level with the highest image quality. We recommend to set this to 65-70%.

Make sure to click `Apply` to save the changes. apply

6.2.2   Ftp Database

4

This action will create and automatically update a text file on the ftp server, containing information about vehicle number plates recorded by the ALPR.

Set Enable to true for the action to be executed (as shown on the image) .

Enter the Host ftp server IP address. Username and Password of the ftp server should be written in the form of: [username]:[password]. Example: for the user name "user123" with the password "pass123" the correct form is user123:pass123 .

Filename stands for the name of the database to be updated (created) with newly recorded information.

Naming patterns define the database entry string. How to form naming patterns read in Chapter 11.

Make sure to click `Apply` to save the changes. apply

6.2.3   Store

5

Set Enable to true for the action to be executed (as shown on the image) .

Define the name of the Folder and the Postfix.

The Postfix field must not be left empty. It is the part of the name which will be appended after the name and the extension.

Minimal free disc space required to save the file is defined by 'Free space' parameter. If there is less space than defined here the files will not be saved.

Make sure to click `Apply` to save the changes. apply

6.2.4   Digital Out

6

This action will produce digital output for a specific time period (Output duration).

Set Enable to true for the action to be executed (as shown on the image) .

Select which Output pin will be activated by the action.

'Output duration' defines the duration of the output signal.

The 'Non-blocking' and 'Invert signal' can be disabled/enabled.

Make sure to click `Apply` to save the changes. apply

6.2.5   Notification

7

Set Enable to true for the action to be executed (as shown on the image) .

Construct a notification for the action using Naming patterns (Chapter 11).

This message will be sent as an addition to the image file.

Make sure to click `Apply` to save the changes. apply

6.2.6   Serial

8

Set Enable to true for the action to be executed (as shown on the image) .

Construct a notification for the action using Naming patterns (Chapter 11).

This message will be sent trough the serial port.

Make sure to click `Apply` to save the changes. apply

6.2.7   TCP

9

TCP (Transmission control protocol) requests re-transmission of lost data, rearranges out-of-order data, and reduces other problems that may occur due to network congestion, traffic load balancing or other unpredictable network behavior. It is optimized for accurate, rather than timely delivery.

Set Enable to true for the action to be executed (as shown on the image) .

Write a message for the action using name patterns (Chapter 11). Enter the IP address of the receiver of the TCP address and the 'Port' used to send the TCP message.

Make sure to click `Apply` to save the changes. apply

6.3   Access control

wi

Enabling Access control ALPR is going to enforce all uploaded lists and related actions. Information about list formatting and uploading find in Section 6.1. .

In case of downloading from the ftp server Download lists from ftp must be enabled, designate the ftp ip address, and enter the credentials for the server. Username and Password of the ftp server should be written in the form of: [username]:[password]. Example: for the user name "user123" with the password "pass123" the correct form is user123:pass123 .

Make sure to click `Apply` to save the changes. apply

6.4   Gate detector

The gate detector feature is used to give control over gates access.

ALPR will process and save a defined number of images, set in Gate detector buffer size. Among those results the one with the highest percentage of certainty will be considered valid for the time period defined in Range of second(s).

Images and/or database entry's can be sent to the ftp when the minimal confidence level is reached.

Gate detector can furthermore be combined with lists, which usage and formatting is explained in Section 6.1. . How to set up the gate detector is explained in the table below.

10 Use Gate Detector Enable/disable the Gate Detector.
Gate Detector buffer size

Set the size of the buffer which keeps last license plate readings. The best matching result is sent to the ftp server.

Recommended to set to 20.

Input IO Trigger Line Define which pin will be activated when the vehicle is detected. There are 32 pins, starting with 0 to 31.
Range of seconds Range of seconds before the trigger switches on in which the plate is considered valid.
Gate detector minimal confidence Determine a minimal percentage of confidence level which a plate must achieve for the results to be sent to the ftp server.
Image ftp server Address and path of the ftp server used for uploading image files to.
Csv ftp server Address and path of the ftp server used for uploading csv files to.
User:Pass image ftp

Enter username and password for the ftp server on which images will be uploaded to.

Form for entering the credentials is as follows: [username]:[password].

User:Pass csv ftp

Enter username and password for the ftp server on which csv files will be uploaded to.

Form for entering the credentials is as follows: [username]:[password].

7   Event Configuration

./images_software/CameraSoftwarePic_28.png

Event Configuration.

There are three types of events:
  • Read event - when ALPR recognizes some plate
  • No-read event - when there are no plates recognized between given limitations set under ALPR Configuration-Trigger (i.e. Start and Stop trigger, or Start trigger and Trigger timeout). More information about Triggers find in Section 5.2.
  • LCR events - Low confidence read event is created when than plate is read but the confidence level is lower than set in parameter 'Event limit of confidence'
For each event fallowing actions can be defined:
  • Ftp Upload
  • Ftp Database
  • Store
  • Digital out
  • Notification
  • Serial
  • TCP

These are same types of actions as in ACCESS Configuration and are in detail described from Sections 6.2.1 - 6.2.7..

8   System Configuration

On this page the following Network settings can be modified:

  • IP Address - set the IP address of the ALPR device.
  • Network mask - set the network net mask.
  • Gateway IP - set the gateway IP address.
  • DNS IP - set the IP address.
  • DNS IP 2 - second IP address, if needed.

After changing these settings the system needs to be Rebooted. Depending on the camera model it might be necessary to power-off and than power-on the camera to complete the reboot process. For older camera models rebooting is done by turning the camera off and on again.

./images_software/CameraSoftwarePic_29.png

System configuration for network settings.

The camera has 32 Input/Output pins listed in the Digital I/O table, starting from 0 to 31.

Interpreting the digital I/O table:
  • Directions- I stands for input, O stands for output,
  • Status- 1 = active, 0 = not active.

This visualizes which pins are active and if they are used for input or output purposes.

./images_software/CameraSoftwarePic_29_a.png

Change the password and upload a classifier on the System configuration screen.

On the image above other features of System configuration page are illustrated.

Changing password for advanced mode can be done by entering a current password, typing in the new password, and re-typing the new password. Click on ,Change’ and the password will be changed.

Classifiers are files which contain state/country specific information. This information can for example be the size an font of letters and numbers, the number of rows the plate is made of, the alphabet used etc.

They will improve accuracy of plate recognition according to the country/state parameter as they support ALPR with features that make recognition easier and more reliable.

Classifiers are made for different regions (Europe, USA, Thailand...). Upload the provided classifier by selecting the file on your computer and clicking on the 'Upload' button.

After uploading a classifier Restart ALPR for the changes to take place.

Finally there is a table with all used Library versions. The first column contains library names, the second a corresponding version number.

9   ALPR Result

View the continuous stream of processed images with an overlay of the reading result.

This OSD differs from the ones on the Configuration pages, as it has a delay. The delay comes from the fact that images displayed are processed.

./images_software/CameraSoftwarePic_30.png

Image streaming in ALPR Result.

On the figure above the processed license plate is displayed underneath the car plate.

We recommend to turn the stream on when configuring the camera, and turn it off afterwards, to save bandwidth and processing time on the camera.

10   Text Result

Processed results can be found in text format in table view. The table consists of:

  • Timestamp-the date and time in which the plate was recognized.
  • License plate
  • Confidence-percentage of confidence for the given license plate
  • Country
  • Country confidence-percentage of confidence for the recognized country

The maximal capacity of results is 1000 and the longest time period for images to stay on the list is 24h.

./images_software/CameraSoftwarePic_31.png

ALPR Text results.

The length of the 'History list' can be set up to 1000 results. When the limitation is reached, the oldest images will be replaced by new images.

In combination with History length, overall result length will depend on which limitation is reached first. If there are 200 entries in 24 hours, results older than 24 hours will be deleted, even when the quantity is not exceeded.

11   Placeholders for naming patterns

Placeholders will customize the result file name.

Placeholders are build out of keywords placed between two percentage signs (%). This form will be replaced with specific information about the reading when ALPR produces a result (i.e. date, time, etc).

Listed in the table below are all keywords and their meaning.

Placeholder Description
   
"%LP%" This keyword will be replaced by the license plate value string.
"%STATE%" This keyword will be replaced by the state string.
"%CONF%" This keyword will be replaced by the confidence value string.
"%CONF_STATE%" This keyword will be replaced by the state confidence value string.
"%NUM_ROWS%" This keyword will be replaced by the count of rows of license plate as string.
"%REGION%" This keyword will be replaced by the region string.
"%REGION_CITY%" This keyword will be replaced by the city string.
"%REGION_SHORT%" This keyword will be replaced by the region short value string.
"%ENDING%" This keyword will be replaced by the state value string.
"%ENDING_SHORT%" This keyword will be replaced by the state value string.
"%COL_PLATE%" This keyword will be replaced by the color of plate as string.
"%COL_CHARS%" This keyword will be replaced by the color of characters as string.
"%POS_X%" This keyword will be replaced by x position in image of left upper corner of license plate as string.
"%POS_Y%" This keyword will be replaced by y position in image of left upper corner of license plate as string.
"%POS_W%" This keyword will be replaced by width of license plate in image as string.
"%POS_H%" This keyword will be replaced by height of license plate in image as string.
"%YEAR%" This keyword will be replaced by year string. (When license plate was detected)
"%MONTH%" This keyword will be replaced by month string. (When license plate was detected)
"%DAY%" This keyword will be replaced by day string. (When license plate was detected)
"%HOUR%" This keyword will be replaced by hour string. (When license plate was detected).
"%MINUTE%" This keyword will be replaced by minute string. (When license plate was detected).
"%SECOND%" This keyword will be replaced by seconds string. (When license plate was detected).
"%FRACSEC%" This keyword will be replaced by fraction of seconds string. (When license plate was detected).
Example:
ALPR has detected a German plate "TEST123" on 01.01.2017 at 10:15:20. You can form the naming pattern i.e. like following:
" License plate value: %LP% from %STATE% " the form will be displayed as : " License plate value: TEST123 from DE "
" Filename_%HOUR%_%MINUTE%_%SECOND%.jpg " the form will be displayed as : " Filename_10_15_20.jpg"
ALPR has detected an Austrian plate "W112233BC" on 15.06.2017 with 89% state recognition certainty, and 100% plate recognition certainty.
" LP_%LP%-%CONF% State_%STATE%-%CONF_STATE% " the form will be displayed as : " LP_W112233BC-100 State_Austria-89 "

Placeholders are replaced with actual data, and plain text stays unchanged.

12   Display formatting directives

These directives are used in time stamp formatting. They will be replaced with specific data on the OSD.

On the table below all the directives with their usage purpose are listed.

Directive Meaning
%a Abbreviated weekday name.
%A Full weekday name.
%b Abbreviated month name.
%B Full month name.
%c Appropriate date and time representation.
%d Day of the month as a decimal number [01,31].
%H Hour (24-hour clock) as a decimal number [00,23].
%I Hour (12-hour clock) as a decimal number [01,12].
%j Day of the year as a decimal number [001,366].
%m Month as a decimal number [01,12].
%M Minute as a decimal number [00,59].
%p Locale’s equivalent of either AM or PM.
%S Second as a decimal number [00,61].
%U Week number of the year (Sunday as the first day of the week) as a decimal number [00,53]. All days in a new year preceding the first Sunday are considered to be in week 0.
%w Weekday as a decimal number [0(Sunday),6].
%W Week number of the year (Monday as the first day of the week) as a decimal number [00,53]. All days in a new year preceding the first Monday are considered to be in week 0.
%x Date representation.
%X Time representation.
%y Year without century as a decimal number [00,99].
%Y Year with century as a decimal number.
%Z Time zone name (no characters if no time zone exists).
Example:
%A-%m-%d %H:%M:%S.%f will display : Friday-06-23 08:12:29.127
%x %H:%M:%S. will display : 06/23/17 08:12:29.127