1.1   Secure communication with the Plate-i Camera

From CARRIDA Version 4.5.0 on, secure encrypted communication with the camera is possible using the HTTPS protocol and a specialized version of CARRIDA. This feature enables encryption of all communication for log in, data transfers with the user interface (including login) and all REST API calls.

If SSL is enabled on the camera, HTTP requests are automatically redirected to the HTTPS communication protocol.

2.1   Logging into the camera

Before the camera can be accessed from a web browser, you have to provide your credentials by logging into the device. The Plate-i user interface offers several levels of access control with different sets of permissions. Only the super user and administrator are allowed to modify all settings and parameters.

The username and password are typically provided by the administrator of the camera(s), but a set of default users is stored in the camera. The factory login settings (login_name/the_password) are as follows:

SuperUser (su/car0000rida)

Access to all settings. May delete admin users, has access to interface design settings. We recommend to not use this login only if absolutely necessary.

Administrator (admin/secret)

Access to all settings. Has the authority to add and delete other users.

Basic user (user/simple)

Access to the most commonly used settings, no system critical parameters may be changed.

Setup: (setup/setup)

Access to the live view and reading results. Has the authority to change the ROI and classifier settings.

Viewer (viewer/pass)

Access to the live view and reading results. Not allowed to change any settings.

3.1   The User Menu

Located in the upper right corner of the live page is the User menu which allows you to easily switch between user profiles. For example, you can switch between a regular user and the administrator here.

3.2   Language Settings

With the languages button located in the upper right corner you can select among the languages supported by the camera. The default language of the interface is English. In addition, the camera offers:

The main purpose of the Live Result page is to verify that the camera is operating properly.

In addition, this page provides useful statistical information to help you optimize the configuration of the CARRIDA setup.

The top of the browser window displays the text configured in the Display Info Text field, the currently activated country classifier, the current time, and the language setting.

3.3   Live Image

A video stream from the camera, together with current reading results, is displayed in the Live Result page. The regions of interest are shown as transparent yellow polygons, reading results are superimposed on the live camera image over the detected license plate. If the display of additional information has been selected in the Settings menu, e.g. info, date and time, it will also be displayed.

The details of how to configure the graphical overlays can be found in Section Display Information.

It is possible to display the video in full-screen mode by clicking on the green button in the lower right corner of the live image. You can leave the full-screen mode by pressing the ESC (escape) key.

3.4   Detection Statistics

The camera collects information about minimum and maximum character sizes visible in plates, and the frequency of detection events.These statistics are displayed in the lower right area of the Live Result Page. You can use this information to optimally configure the Plate-i engine in the Settings page.

The Detection Count shows the number of license plates which have been moving in accepted and forbidden directions according to the setup of each ROI.

Note that the statistic display is reset after each restart of the camera.

3.5   Overview Detection Results

The most recent detection results are listed in the table in the upper right side of the Live Result Page. The result table is immediately updated after each new detection. The update is signaled with an animated green bar underneath the new entry.

4.1   Reading Results

The tables for the Accepted Results and the Wrong Direction Results consist of:

• A Timestamp with the date and the time when the plate was detected.
• The License plate text.
• The Confidence of the given license plate recognition.
• The detected Country of the vehicle license plate.
• The Confidence of country recognition.
• An image of the detection which is currently selected in the table.

4.2   Refreshing Text Results

The result tables are generated when the Text Result page is opened, they are not automatically updated - new entries may be created by the camera while you are watching the text results.

To update any table with the latest results, click the Reload button .

4.3   How to browse the Text Result table

The result tables potentially contains thousands of entries which cannot be displayed at once. If necessary, the results are therefore separated into pages which can be individually loaded from the camera. You can navigate through the pages using the navigation buttons.

• Click on the Previous or Next button to switch a page.
• Directly jump to a page of the text results table by clicking the page number box.
• Type a page number into the GoTo Page field and click the right arrow.

4.4   Searching a table

To get the most out of the result tables,they are fully searchable and can be queried for any given information like plate number, date or time.

The simplest method is to type the text you are looking for (e.g. the license plate string, or only a part of it, or a number) into the search field in the right upper corner of the page. You can search for multiple strings by separating them with a blank character in the search field. In this case, all of the strings must be contained in the table entry.

For example, if you type are looking for text results which contain the text element BR and the number 80, type 'BR 80' into the search field like shown below. Note that the '80' would be searched for in license plate strings as well as confidence values.

The search results can be further refined by restricting them to a

• Date and Time range.
• Plate confidence.
• State confidence.
• The list to which it matches.

The filter option dialog opens by clicking on the button. If you provide only one of the parameters in the parameter field, e.g. only the starting date or the lower confidence value, the opposite parameter is set to a value that maximizes the search range.

The following example below shows how you combine the the text search field and the parameter filter options to look for specific license plates

• which contain the string 'BAC3',
• which have been detected between the 5th and the 7th of December 2021,
• between 7:30 (am) and 15:30 (3:30 pm),
• with a minimum confidence of 80,
• and which have a match in the Blacklist.

4.5   Deleting Entries

Individual entries of the text result table, filtered or unfiltered, may be deleted by selecting the row and then pressing the button.

All entries of the text result table can be deleted by pressing the button.

4.6   Exporting a result table

The content of (a potentially filtered) text result from the table Accepted Results or Wrong Detection Results can be exported from the camera in several different formats. You can choose to export as:

• CSV (comma separated value) file.
• XLS file readable by Excel.
• ZIP archive which contains all images. The naming format of the images is fixed as <timestamp_platestring_confidence_state_confidence.jpg>

Do not forget to update the table with the refresh button prior to export.

4.7   Images linked to text results

The right side of the Text Result page is reserved for images related to text result entries.

The actions and their result states which are connected to this image are listed at the bottom.

5.1   ACCESS Lists

The access lists available on the camera allow you to divide license plates into different categories. The lists may be used for arbitrary purposes, they have assigned names for convenience only.

The available types of Access Lists on Plate-i are:

• Whitelist.
• Blacklist.

Every time the camera reads a new license plate, it compares the string with all entries stored in each list. If an entry matches, the defined action for that list (or none) is performed. Likewise, if the newly found license plate does not match and an action is defined for this case, the action will be performed.

Each list may contain an arbitrary number of license plate texts.You can modify lists by

• editing it manually in the web GUI,
• the button deletes all entries of this list,
• importing them from your PC,
• using the REST API of the camera.

The following image depicts the web interface of the camera which you can use to add lists entries to the Whitelist manually:

5.2   Additional list properties

License plate entries may either be defined as full strings, or as patterns which are called regular expressions.

With the help of regular expressions you can define text patterns, which describe a whole set of strings in a very compact way. For example, you can easily write a regular expression to match all license plates which start with the character 'B'.

A list entry contains at least the plate number, but it can optionally contain a date- and time range as well. Only text matches within the defined date and/or time range will then be accepted as valid. Even several date- and time ranges per license plate are allowed.

Note

The camera checks once per hour if any of the lists contains an expired license plate text, and deletes any outdated entries. This is to make sure that lists cannot grow indefinitely.

5.3   Manual creation of a list entry

A new list entry can be directly created using a dialog in the camera's interface. Click on to open the Add List Entry dialog.

If you click a list entry, the edit dialog for this entry opens.

The first entry in the dialog box is the license plate text. Turn the Use Regex switch ON, if the text shall be interpreted as regular expression.

When Always enabled is turned ON, a match will not be restricted to a specific time or date range.

When Always enabled is turned OFF, time and date limits apply. They can be defined through the date and time fields at the bottom of the dialog. The time range for the validity of a license plate can be defined through

• the start and end date,
• start and end time,
• and on individual days of the week marked as So, Mo, Tu, We, Th, Fr, Sa.

A new list entry is pre-set with a time range from 00:00 to 23:59 (the whole day), and Monday to Friday, for a month from the current date.

In the example in the dialog shown above, Mo-Fr is checked, meaning that if an LP is detected on any working day between the set dates, any defined action will be triggered.

After finishing the list entry details, click on Add (the green plus button) to add the time/date details to this plate text, and repeat if necessary.

Click to add the new plate entry to this list and close the dialog.

Click to discard your edits and close the dialog.

The button deletes this entry from the list and closes the dialog.

5.4   Import of list files into the camera

If a larger number of license plates needs to be maintained, it is more convenient to import a text file which contains the license plate data and associated date/time range definitions.

To this end CARRIDA provides an import dialog which allows you to upload and check a properly formatted text file.

The following steps are required for an import:

1. Create the text file according to the Formatting rules for external files described in the next section.
2. Select the list you want to import to.
3. Click on the select button and select the text file from your PC.
4. During the import of the text file, all entries are checked for validity, only valid entries will be imported and used.
5. You can choose whether an uploaded list replaces the current list in the camera, or if it is being appended.

.+

[0-9]+

.+TX

[A-Z]+.*[0-9]+

CAR[0-9]{3}

5.5   Actions

Once the camera detects a license plate, it checks whether some action has to be taken based on this reading. Sources which may trigger actions are

Read events

occur when the camera detects and reads any license plate.

NoRead events

occur when NO plates are detected in a triggered reading mode. The use of external triggers is explained in detail in Section Trigger.

Wrong Direction read events

occur when a new license plate is detected, but it's moving in a direction that is not within the allowed direction range, i.e. it moves the wrong way.

Whitelist match, Blacklist match

if the license plate is found in one of those lists.

Whitelist mismatch, Blacklist mismatch

if the license plate is NOT found in one of those lists.

Timed Actions

are triggered by a timer in regular intervals. For example the camera can be configured to send a live image to a server once every hour.

The definition of actions is done from the Actions menu of the Access page. Here you can choose which action should be performed based on the event type.

Ftp Upload

Create a new file from the reading result and transfer it over ftp.

Ftp Database

Update a database file on an ftp server with the new reading.

Store

Save the current image in a specified location on the camera.

Serial (only available on selected camera models)

Format and send a message over the serial port of the camera.

TCP

Format and send a TCP message.

HTTP

Format and perform a request on a specified HTTP server.

HMACHTTP (only available on selected camera models)

Use the HMAC protocol to allow secure communication with a server.

MQTT

Publish a message to an MQTT server.

Digital Out

Set a digital output line of the camera for a specified time.

5.6   Placeholders

All actions which create messages or files can use placeholders for actual values of an event. For example, an action may create a filename which uses the actual license plate text and/or the current date and time. This feature allows you to create dynamic actions, which are much more useful and give you more flexibility for the integration of the camera into your environment.

Placeholders have the form %placeholder-name% - this text will be substituted by the actual dynamic element information when the action is performed.

A complete list of placeholders can be found in Placeholders for naming patterns.

Some special characters are internally represented as placeholders. If you need them in action texts, you can write them literally in the action text, or optionally use their placeholder representation:

,          or   %COMMA%
( )        or   %BR_ON%       %BR_OFF%
[ ]        or   %SQ_BR_ON%    %SQ_BR_OFF%
=          or   %EQUALS%
&          or   %AND%

You always have to use placeholders for carriage return and linefeed symbols:

<CR, ASCII code 13>: %CR%

<LF, ASCII code 10>: %LF%

The current list of available placeholders is shown when you edit a filename dialog:

5.7   Adding Actions

To add an action, first choose the event category for which the action is to be added, then press to open the configuration dialog.

The Add/Edit Action Dialog changes dynamically based on the type of action you want to define. The next section describes each of the action types and how it is to be configured.

5.8   Actions and their definition

This section describe in detail all possible actions that can be triggered by an event.

Each action must be enabled by sliding the Enable button to the right, .

Actions may be valid on one of the defined ROIs (see Section ANPR Region Of Interest) or on all ROIs. Use the pull down selector to specify which of the areas shall trigger the action.

Finally, before you save an action to the camera, you can test it by pressing the button and so find invalid parameters, server names etc.

5.8.1   Ftp Upload

Used this action to transfer image files of detected plates to a remote ftp server.

Enter the Host ftp servers IP address in the form of (s)ftp://192.168.3.127/[...].

As authentication you may choose between

User/Password Authentication

Username and Password of the ftp server should be written in the form of [username]:[password].

Example: for the username "user123" with password "pass123" the correct form to enter is: user123:pass123.

Private Key Authentication

Select a private key file which is to be used for authentication.

The Naming pattern specifies the filename to be created on the ftp server. You can use any of the CARRIDA placeholders to generate a dynamic filename:

With a selection of the Image Upload menu you can select how images are cropped dynamically:

Empty file

Create and empty file only, no image transfer.

Full image

Transfer the whole image.

LP Image

Transfer only the license plate image.

Cropped Image Size Relative Image

An image cropped around the LP with a size in % relative to the original size and scaled to 'Final Image Width/Height' dimensions.

Cropped LP Size Relative Image

An image cropped around the license plate with a size in % relative to the original license plate size and scaled to 'Final Image Width/Height' dimensions.

The parameter Image quality refers to the JPEG compression of the transferred image. Its range is between 1 to 100%, 1% being the maximal compression level which will produce images with the lowest quality, and 100% being a minimal compression level with the highest image quality. We recommend setting this parameter to 50-70%.

If your CARRIDA camera supports a second camera (e.g. CARRIDA on a Jetson Nano board), an additional Upload Overview option will visible in the action dialog. It allows you to also transfer the full image of the overview camera to the ftp server.

Use the button to check the ftp connection after you have specified all access information.

5.8.3   Store

Warning

This action is recommended for expert users only!

This action stores images directly on the camera. Use this action type to collect images for later use. This feature is mostly used for testing, it can also be used to collect images for training and development purposes to improve CARRIDA.

The filename is constructed of a path name, and a dynamic filename, which may contain any placeholder. Note that we recommend using the file path /root/data as a storage location on the camera.

Images can be cropped and uploaded as with the ftp action type, they are only stored on the camera if at least Min Free Space (MB) Megabytes of free space is available on your edge device.

5.8.4   Digital Out

This activates a specified digital output line on the camera for a given time period (Output duration).

Select which Output pin will be activated by the action. Output duration defines the duration of the output signal in ms.

The Invert signal option inverts the polarity of the IO line.

5.8.5   Serial

Construct a message using text and placeholders and send it through the serial port of the camera with the specified Baud rate.

The message field may contain any plain text and the CARRIDA placeholders.

5.8.6   TCP

Send a message using TCP protocol.

The message field may contain any plain text and the CARRIDA placeholders. The IP address and Port of define the network address of the receiver.

5.8.7   HTTP

Perform an HTTP action with the specified Request Type

• POST,
• PUT,
• DELETE,
• PATCH.

to server address given in URL.

The message field may contain any plain text and the CARRIDA placeholders.

As authentication you may choose between

Basic

Supply the Username and Password for the HTTP(S) server.

Certificate Based

Select a private key file which is to be used for authentication.

5.8.8   HMAC

Note

This Section does only apply to selected CARRIDA camera models.

The HMAC protocol allows yo to define messages for secure communication with a server in a flexible way. The setup dialog for HMAC in CARRIDA is implemented with this flexibility in mind. You can mix fixed text elements with the typical CARRIDA placeholders in order to create dynamic HTTP headers and body texts.

The following description assumes that you are familiar with the use of the HMAC protocol.

The HMAC dialog of the action definition is shown below, it allows you to specify all necessary request elements for communication with a server.

The HTTP request type for this action is selected from a pull down menu:

The URL parameter defines the server address.

The Body parameter allows you to specify the message body, including the usual placeholders.

The Key parameter allows you to specify the key value, which is used to encrypt the message hash.

The Hash parameter specifies the elements of the message for the computation of the message hash. You can mix text fields with CARRIDA placeholders:

The Header list parameters specify which elements are combined to make up the HTTP message header. You can add an arbitrary number of elements to the list by clicking the button, or remove an existing entry by clicking the button.

The following image shows you an example of an HMAC specification as it could be used to communicate with the server in a data center:

5.8.9   Timed Actions

Timed Actions are a special class of actions which are triggered by a timer in regular intervals. The action types you can use are the same as in all other events described in the previous sections.

A timed action starts at a specific time Action Time and it will be activated with a returning interval defined by the fields Days, Hours, Minutes and Seconds.

6.1   Configuration of MQTT settings

The tabulator page Actions->MQTT presents you with the current list of MQTT servers which you have setup so far. You can add a new server anytime and use its ID as reference in action definitions (see below).

You can add a new server with the button, remove an existing server from the list with , and configure a server with .

The MQTT server configuration page allows you to configure the server connection as needed. All global server parameters are setup here. Individual messaging details are configured in the MQTT action dialog.

If you check the Last Will flag, the dialog extends to present you with the options necessary to define an MQTT last will configuration.

After the configuration of all server parameters is done, you can save the setup by pressing .

In order to confirm your settings and connect to the new MQTT server, click the button. The connection is being built up and thus tested. You do not need to connect with this button before an action can be used!

6.2   MQTT Publishing

Actual MQTT messages are published from within actions, as it is done for the other supported message types like ftp.

A MQTT message is defined in the MQTT action dialog.

The Server pull down menu allows you to choose one of the setup MQTT servers, the parameters topic, QOS are the standard MQTT protocol elements used for this message.

You can construct a message which is made up of text, all the possible placeholders, and images using the respective placeholders.

7.1   Overview

The Settings page groups all camera parameters into several logical menus, which can be opened and closed by clicking on the triangle next to the menu name.

7.2   Camera

The Camera settings page is used to optimize the imaging performance of the camera.

7.3   Trigger

The Plate-i camera can be triggered by external signals. These trigger signals can enable and disable the operation of the camera in a flexible way.

Within a trigger period, when the camera is active, it behaves like in free running mode. This means that reading and sending of LP texts, list matching etc. is performed as usual.

If no LP has been detected at the end of an active trigger period, the camera can optionally create a NoRead event and perform an action. This feature may be useful if you are expecting a vehicle within the trigger period, but it fails to show up.

The trigger type parameter is used to select the trigger source.

None

When selected, the trigger mode is turned off and the camera operates in free running mode. This should be the default mode when an external trigger is not available or not required.

Digital I/O Lines

The trigger signals are provided using the available I/O lines on the camera. It is possible to use a single I/O line to Start and Stop, or you can send the Start and Stop signal using separate I/O lines.

Note that the IO trigger type may be unavailable on your device.

TCP

This trigger type allows SW triggering. Send a TCP message from your server to the camera IP address + port.

HTTP

This trigger type allows SW triggering using a simple REST API.

Send a HTTP GET request to

• Endpoint http://camera_ip/trigger/start as Start signal
• Endpoint http://camera_ip/trigger/stop as Stop signal

7.4   Engine

The preset default values of the Plate-i engine usually result in good reading results, but they can be modified to tune the OCR to specific application requirements.

The Settings page with opened Engine tab on the right side shows you a live image of the camera with additional information superimposed. The main purpose of the live image is to allow you to set up the Region of Interest (ROI) in the image within which reading is performed.

The following three Sections introduce you to the basic concepts of ANPR Regions of Interest, ANPR Regions of Interest with motion, and how license plates close to the image border are handled.

7.4.1   ANPR Region Of Interest

The ANPR Region of Interest (ROI) is the yellow polygon superimposed on the camera image, it defines the image region were the actual reading takes place.

In addition to the image location, the detection area may also specify a direction and direction range of motion or a distance change qualifier - this is explained in Section ANPR Region Of Interest with Direction below.

A ROI polygon can have an arbitrary number of contour points, but it must contain at least 3 points. The corners of the polygon are marked as small yellow circles with the area number inscribed (see screenshot above). The shape of the polygon can be modified as follows:

Adjusting the ANPR ROI polygon

Click, drag and release a corner of the polygon to move it.

Add corner points by double-clicking near an existing corner point. The newly created point can then be dragged to its new location.

Delete an existing corner point by moving the mouse over it and right click.

Move the entire polygon by pressing ctrl on the keyboard and dragging a corner with the mouse. This moves the whole polygon.

More than one region of interest can be defined by setting the number of desired regions in the Number of Areas box. You can also provide a custom name for an area which can be used in Actions as reference to this ROI.

The example below shows a definition of two ROIs. Note that the small images are actual live images from the camera. The areas have been given the names Entry Lane, and Exit Lane respectively.

7.4.2   ANPR Region Of Interest with Direction

An region of interest may be combined with a motion filter so that license plates are only accepted if they move in certain directions.

You can choose the type of motion filter with the pull down dialog next to Motion Matching:

Disabled

No motion filtering is used. Any license plate within the area is accepted.

Direction Angle

A license plate must move in a defined direction in order to be accepted.

Directions are visualized as green/red sectors - green sections mark the accepted driving direction, red sections define invalid directions.

In the example below, a direction from lower left to top right of the image with an angle range of approximately 140 degrees is allowed. The accepted center line of allowed motion direction of licence plates is marked by the yellow arrow.

Distance Change

A license plate must either approach the camera, or leave the camera in order to be accepted. The direction estimation is based on the size change of the license plate between readings.

Note

It is only possible to compute a motion direction if at least two detections of a license plate have been made. When the minimum number of detections is set to 1, the situation may occur that only one instance of a license plate has been detected as valid. In this situation, the license plate is accepted regardless of the direction and range specification of the ROI.

In order to use the motion direction filter, the minimum number of detections must be set to a value >=2.

7.4.6   Easy configuration of Min/Max character height

Instead of using numerical values for the min/max character height, you can change those values interactively in the live camera view of the settings page. The currently accepted character sizes are visualized as overlay, where the two E characters resp. the light green rectangle show you the accepted size range:

Click on the this overlay with the mouse to adjust. Note that the numerical parameters in the value fields on the right side are synchronized accordingly.

Adjusting the accepted character sizes

Click and drag the upper border of the rectangle to modify the accepted maximum height.

Click and drag the lower border of the rectangle to modify the accepted minimum height.

Click and drag within the text Accepted Character Height to move the rectangle.

In the following example, the overlay has been dragged to the actual license plate location and adjusted:

7.5   Parking Mode

The Plate-i camera operates in Parking mode, which means that it reads a new license plate constantly, but transmitts it only once - it returns only unique license plates and suppresses multiple readings.

You can reset the suppression of identical readings with the setting in Reset After (s) to retransmit a LP after the timespan defined here.

If Reset After (s) is set to 0, readings will never be retransmitted.

7.6   Display Information

The set of parameters in the Display Information menu allows you to configure the display of information in Live View with the On-Screen-Display (OSD).

Enabling/disabling any of these options will take immediate effect on the live image display.

8.1   System Actions

With the System Actions menu in the right upper area of the Configuration page you can to perform basic maintenance functions.

8.1.3   Save Configuration

The complete set of camera configuration parameters can be exported and stored on your PC with this button. This feature may be useful in order to make a backup of the configuration, or even to transfer the settings to another camera.

The following parameters will be saved:

• classifiers
• date and time settings
• network settings
• parameter settings and region of interest definitions
• users and their permissions
• access lists
• action definitions
• information about CARRIDA software versions on this camera
• the serial number of the camera

A popup window informs you about the progress while the export is being performed.

8.1.4   Import Configuration

The state of a camera can be restored by importing a previously saved configuration file using this system action.

It is possible to import configuration settings from another camera - this may be useful when you want to quickly copy and distribute camera setups.

For best compatibility, we recommend that you exchange only configuration files of the same firmware versions.

A warning dialog will appear if the serial number of the imported configuration and the actual camera are different. You will be asked to choose whether to proceed with the import, or to cancel it.

You can choose which system settings to import by enabling or disabling features from the import dialog. By default, the import of all features is turned off so that you have to manually select what you want to import. After making your selection, press the import button to proceed.

After the import is finished, a confirmation window appears to inform you about the settings that have been restored and to notify about a reboot which is necessary at this point.

8.1.5   Ini Editor (Super admin only)

Warning

The INI editor should only be used if you know exactly what you are doing! You need to have super admin rights.

If you are logged into the camera as super admin (su) user, you have access to a low level configuration editor for the camera. The Ini Editor allows you to modify some low level settings of the firmware, which are otherwise not accessible.

Be extremely careful when modifying one of these parameters, the camera may be rendered unusable with a wrong setting.

A new INI parameter may be added using

Add the desired section name, the key name, and a parameter value, then press .

8.1.6   Update Software

CARRIDA may provide a software update for your camera as an update package, which can be installed using this menu. Select an update package by pressing the Select File button in the lower third of this dialog and click to start the update process.

Note that usually a SW update will not modify your camera setup, but it may be the case for certain types of updates.

Depending on the update package provided, you will have to restart the camera firmware.

8.2   Network

In this configuration page you can setup the network connection of the camera:

• DHCP - use DHCP on/off
• Hostname - set the host name of the camera
• IP Address - set the IP address of the camera
• Network mask - set the network netmask
• Gateway IP - set the gateway IP address
• DNS IP - set the DNS IP address of the camera
• DNS IP 2 - set an optional second DNS IP address

Any of the above parameters can be changed by clicking on the Edit button, as shown in the image below:

8.3   Time

The Time menu allows you to set the current time on the cameras as well as the local timezone.

You may either set the date and time manually,or use a time server in the network to automatically sync the camera clock with an external source.

8.3.1   Manual setup of date and time

A click on the Edit button brings you to the time setting edit dialog.

In order to manually set the camera's time, NTP has to be turned OFF by sliding the NTP knob to the left.

First select a timezone using the pull down dialog Chose Timezone, then manually enter date and time in the Set Time field.

By pressing , the date/time settings will be saved and the dialog is closed.

8.3.2   NTP Protocol

You may configure the camera to automatically synchronize its internal clock with a time server in the network using the NTP protocol. Typically ypur edge device is pre-configured with a list of standard NTP time servers, but you can customize the server list if necessary.

A click on the button in the Time page brings you to the time setting dialog. When you enable the NTP protocol by sliding the selector button at the top, , the list of active NTP servers is displayed and may be edited:

Press the or button to add or delete servers. You still may choose a timezone, but not modify the date and time display.

Pressing saves the date/time settings and closes the dialog.

When NTP is enabled, the current status is displayed below the NTP parameters. Note that this lists shows the NTP servers used by the current NTP configuration on your system.

8.4   Users (User Management)

CARRIDA allows you to manage a number of user profiles which are differentiated by the level of access to configuration and system settings of the edge device.

By default, each user has the following sign-in credentials:

After clicking on the Create new button, use the pop-up dialog to create a new user profile.

8.4.1   The CARRIDA Super User

The SuperUser with username su has full permissions to modify all aspects of the camera. The default password for the super user is constructed using the serial number of the camera as follows:

car<SN of the camera>rida.

Note that the serial number of the camera is only available on the Carrida Cam Pro and CARRIDA Cam Basic+ models. All other supported devices, including Plate-i, use the code '0000' as default serial number. As per factory default, the SuperUser password is set to car0000rida on those devices.

It is highly recommended to change the default password for the super user immediately during setup of the camera.

When you log in to a camera as super user for the first time, you will be prompted with a dialog window and asked to change the super user password.

For later password changes the standard method should be used as described in the Section Users (User Management).

8.5   Regions

Country specific details of license plates are stored as Region files on the camera. They are created for different countries, or regions of the world (Europe, USA, Thailand...) by CARRIDA.

The CARRIDA camera stores region files as a part of its firmware, and this list of region files may be updated and expanded by the user. The Region menu of the Configuration page allows you to upload new regions, delete old ones, or activate any region information which is stored on the camera.

The currently available region files are listed under Available Regions below.

Note that only one Region may be active on the camera at a time, but a region file can contain information about an arbitrary number of countries (e.g. all countries of the EU).

8.5.1   Switching Regions

As mentioned above, the camera can store a large number of classifiers as a part of its firmware, and those classifiers can be selected and activated anytime. To do so, click on the edit icon, this opens a dialog with a drop down list of classifiers.

By selecting a new entry from the list and pressing , the selected classifier will be activated. Note that a classifier change requires a restart of the internal ALPR software and may take up to a minute on your device.

8.5.2   Uploading Region Files

The list of available regions can be extended by uploading new region files to the camera. In this way you can configure the camera for new regions of the world, or update and improve its existing reading capabilities.

New regions can be uploaded by clicking the button. This brings up a dialog window into which a new region file can be dropped ('Drop region file here...').

Alternatively, a click into the rectangular drop box opens a file selection dialog.

When uploading a new region, you can opt for deleting all other stored region files by turning on the option Delete other regions. Use this option with care!

8.6   SSL

If you enable the SSL protocol on the camera, the communication with its webserver (including all HTTP based communication like the REST API) becomes much more secure.

The SSL page allows you to setup SSL and upload the required certificate files.

Before you can use SSL, you have to enable it by sliding the Use SSL switch:

When SSL is enabled, a number of action buttons appear in the lower right field of the page. You can use those to upload

• certificate chains to the camera using the button,
• certificate files to the camera using the button,
• an SSL key using the button.

If the private is also encrypted, set the Private Key Encrypted switch on, and provide the password in the text field below:

8.7   System

The system menu page displays general information about the camera software versions, disk usage, as well as the status of the available digital input and output lines.

9.1   Style Change

In order to provide the possibility to personalize the CARRIDA UI, the website color design is split into multiple groups. The color for each group can be edited independently by clicking :

• Primary and secondary colors The color of the page details such as buttons, table headers, and navigation.
• Error color The color of error status visualizations.
• Font color The color of the text elements.
• Body color The color of the body background.
• Sidebar color The color of the navigation sidebar.
• Card color The color of the background of UI cards.
• Panel color Color of the panels contained in the access and settings pages.
• Border Radius The radius of corners drawn for various design elements.

The Style menu contains a table with the current values for all properties. These values can be edited by clicking into the numeric field of each element. A pop-up editor contains a color picker for color values respectively a number input for the border radius (see also the screenshot above).

Changes you make are immediately visible in the live user interface.

Click to permanently save changes.

The Reset to default values button can be used to revert the UI back to factory settings.

Use to exit the UI design page without saving.

Do not forget to clear the browser cache after reset of the style elements!

9.2   Icon change

Each icon which is used in the Plate-i Web interface can be replaced with a custom version. This allows you to adjust the Plate-i interface to your corporate design.

All currently used icons are displayed in the Icons tab. By clicking on any of the icons, a dialog window pops up with the options for icon replacement. You can choose to upload a new icon image or to reset it to the default version.

After changing the icon, a message dialog window with the notification about the status of the changes will show.

10.1   IP Address Configuration Check

The camera makes a sanity check of the network configuration during reboot (power on) and server restart. If the network configuration is not valid or empty, the configuration will be reset to factory defaults. This will enable you to get access the camera under the factory default IP address.

Note that the ANPR settings will not be modified.

10.2   Server Configuration Check

The camera makes a sanity check of the ANPR server configuration every time at which the server is restarted. If the configuration is empty, or seems to be obviously invalid, it will be reset to default values.

An invalid server configuration may be created for example when the camera suddenly loses power. In this case it may happen that configuration files are not written properly to the internal flash memory.

11.1   Automatic replacement of special characters in Action texts

Some special characters are automatically replaced internally with a placeholder representation. Those characters can be freely used within actions texts:

, ( ) [ ] = &

use the following placeholder sequence for

<carriage return, ASCII code 13>: %CR%

<linefeed,ASCII code 10>: %LF%

14.1   CARRIDA Edge/Plate-i 4.8.3

This is the first official Plate-i release.

14.2   CARRIDA Edge 4.8.2

General Improvements

• The resolution settings have been removed in the camera menu. The camera uses always high resolution.

This is the first release for the Plate-i devices, based on CARRIDA Edge 4.8.1.

Bugfixes

• Network settings have been improved for DHCP.

14.3   CARRIDA Edge 4.8.1

General Improvements

• Logging has been improved.
• General performance improvements
• Corrected order of licenseplate characters in plate result value field for arabic plates.
• Added Stop On Detection flag that can be used in timeout trigger mode.

Bugfixes

• [CRITICAL] Heat map calculation corrected in the case of plates that are detected at the image border.
• Factory reset improved.
• Visualisation of detection areas improved.
• Configuration of export and logs downloading dialog visualisation improved.
• VEHICLE_CLASS placeholder corrected in the Tag Suggestions dialog.
• HTTP HMAC action editing corrected.
• fps read visualisation in trigger mode corrected.

WebGUI

• Extended statistic visualisation added (charts for basic camera settings for the range of up to one week can be displayed).
• Action testing timeout added. (Testing of not correctly defined actions is stopped after 20 seconds).
• Start-Sequence trigger mode removed.
• Access lists visualisation improved.

CARRIDA 4.7.1 SDK

• Improvements in plate filtering algorithm.
• Improvements (both runtime and recogntion performance) of the vehicle classification algorithm.
• New draw options flags (vehicle class, position, confidence).
• Updates of Germany regions database.
• General improvements of the recognition performance.

14.4   CARRIDA Edge 4.8.0

CARRIDA Edge version 4.8.0 is a release with major additions to the functionality of the camera interface, in addition the CARRIDA SDK 4.7.0 has received some significant updates and improvements.

Bug Fixes

• Server Improvements The anpr server has been made more reliable and robust.
• v4l2 camera handling has been improved.

General Improvements

• Vehicle classification can be computed if it is supported by the classifier. Contact CARRIDA for more information and new classifiers.
• MQTT publishing has been added with support of all MQTT publishing features. You may configure one ore more MQTT servers to which you can publish results and images.
• FTP actions can optionally use public key authentication now.
• HTTP actions now support optional certificate based authentication.
• REST API functions have been added to include all new parameters and functions of this release, specifically statistical information can be retrieved now.

WebGUI

• Apply buttons have been removed in all pages wherever possible. A new value is stored by the interface as soon as you type or click it, making the process to configure parameters much more efficient and faster.
• New parameters have been added: Enhanced detection, Advanced state classification, Main country(-ies), Plate verification, Distance change.
• Visualization of results and confidences has been improved. A new design for the display of results has been created.
• The Camera types configuration has been re-organized and improved.
• The visualization of state recognition has been improved.
• The INI Editor can now add new parameters.
• Statistics of the edge device operation and other useful information is now displayed in the WebGUI. Future releases will add more parameters.

CARRIDA 4.7.0 SDK

• Plate verification feature added for a better suppression of unwanted readings.
• The exact license plate position can be provided now. The exact corners of a license plate are computed and stored at the cost of slightly higher computing times.
• Main state(s) can be optionally defined - this state and its neighbors will have higher priority for state-recognition.
• Significant improvements in state recognition for USA and Canada.
• Faster processing in stream modes.
• New parameter SortResults introduced (see documentation of CARRIDA parameters), can be used to reduce latencies for the fastest readout possible.
• Distance_change_type option added (differentiate between approaching/leaving/static vehicles). Detects if a license plate is approach or leaving the camera, based on size changes of the detected license plate.
• Hashing of a license plate string is possible to guarantee anonymity of readings. A hashed string can be used in actions to transmit and store license plates.
• Optimizations in the handling of ANPR readings which are located close to the ROI border(s).

14.5   CARRIDA Edge 4.7.0

CARRIDA version 4.7.0 is a release with major additions to the functionality of the camera.

Bug Fixes

• Factory Reset bug Running a Factory Reset (or import with Import Classifier selected) causes UI to freeze (temporarily) and factory reset is not performed.
• Logs download bug Larger log files could cause the error while downloading logs. This bug didn't occur as long as log files don't reach critical size.
• Result REST API call An error in text results filtering caused return of empty lists

General Improvements

• 3 digit country code CARRIDA can handle ISO 3166-1 alpha-3 country codes in addition to currently used 2-digit country codes. New country code is also added as:
  • a placeholder for actions
  • a field in the JSON output.

WebGUI

• Test action button Implement a test functionality for actions. Every action dialog contains a test button so that the action can be dry-run without real event.

• Access List upload extend option Add option to select if the list should be replaced or extended while uploading new list file.

• Tooling functions Added a modal dialog that contains interface to run following terminal tools:

  • traceroute
  • ping
  • ip info

• Draw confidences on/off feature The drawing of confidences in the visualization of license plates is now optional. It can be switched on/off using a parameter in Display Information section.

• Access list filter for text results Added a filter option to display text results that have been matched to the access lists at the time of reading.

• Timed actions New type of actions which are triggered by a timer. Actions are defined with 2 additional parameters:

  • start time (hh:mm:ss) - time of the day which defines the time of first run of the action
  • running interval (hh:mm:ss) - interval that defines time span between two sequential runs of the defined actions.

• NTP status NTP status is shown on Configuration page if NTP is enabled.

CARRIDA 4.6.0 SDK

• fast vehicle classification implemented - vehicle class (motorcycle, car, van, camera, truck, bus) and vehicle brand (e.g. Opel Astra)
• Country Alpha-3 code added as part of license plate output
• improvements for UAE - state recognition, color detection
• General improvements of the recognition performance

REST API

• Add SSL Features to REST API The REST API needs to be expanded so that the new webGUI SSL features can be used using REST:

  • upload keys, certificates
  • enable/disable SSL

• Statistic API endpoint There is an endpoint added to the API server. It can be used to obtain statistics as json object. That object contains detections count, characters heights and heatmap. Each of this statistics part can also be obtained separately.

• Make and Model On certain devices available. In the case that make and model detection is enabled, related entries are added to the result tables (live and text), to the json struct in the rest API and new placeholders are also available in the action fields.

14.6   CARRIDA Edge 4.6.1

Bug Fixes

Several Bugs have been corrected in this release:

• Corrected bug which did not properly display the direction indicator of the ANPR engine page in Firefox.

• Corrected a bug in the REST API, set parameter works now:

  • min_gain, max_gain, min_shutter, max_shutter
  • lowConflimit
  • MinLetterHeight, MaxLetterHeight

General Improvements

Several checks and safety measures are now integrated into the camera, so that in the case of data corruption access to a camera is still possible.

• Addition of the check for a DIO reset signal during the first seconds of a camera boot If a reset input sequence is detected, the network interface of the camera is reset to default values.
• The camera makes a sanity check of the IP configuration during boot and server restart. If the IP config is not valid or empty, the IP configuration will be reset to factory defaults.
• The camera makes a sanity check of the anpr server configuration. If the configuration is empty or seems to be invalid, it will be reset to default values. This does NOT affect the network configuration.

CARRIDA Engine 4.5.2

• General improvements of the recognition performance.
• The handling of wide characters like 'M' or 'W' has been improved.
• FilterNonPlates parameter added to better suppress unwanted readings.
• Bugfix for UAE (a letter must always precede digits).
• The engine is now initialized quicker.
• Reliability of the confidence output has been improved.

WebGUI 4.6.1

• Opening a specific GUI site on the camera (e.g. 192.168.13.23/configPage) will open this page after the login dialog. Calling the camera IP without a subpage target will open the home screen.
• Added a button to reset the live statistics on the live page.
• An IO trigger option is only available if an input line is configured on the camera.
• NoReadEvents are now stored and displayed very similar to the other text results.
• The top of the GUI window shows additional info.
• In the settings menu, drawn polygons (brightness control and ANPR region) can be moved by pressing ctrl and dragging a corner with the mouse.

REST API

• Bug fixes.

14.7   CARRIDA Edge 4.6.0

Bug Fixes

Several Bugs have been corrected in this release:

• The syncing of the ANPR ROI and Brightness ROI works now correctly, even if one of those areas is not defined.
• Actually run a no read action in trigger mode when there was no plate detected during the active reading phase.
• A freezing screen while loading no read logs has been solved.
• Bug in visualization of the matched lists in text result page. The matching was performed, but not displayed correctly.
• problems in the web UI when editing UTF-8 plate entries.
• Bug in REST call in*/properties/roi* which created an internal server error as response.
• Import design settings was not working smoothly. Progress bar was not shown, button stayed disabled after import.
• When editing a list entry. the Save button in the dialog was not disabled, thereby preventing further editing of the affected list without a manual page refresh.
• Editing of ROIS in Settings: ensure that each new point added by double-click is within the image area.

SDK 4.5.1

The CARRIDA Engine has been improved and enhanced to deliver more performance and accuracy.

• A noticeable performance improvement, you can expect up to 20% faster reading. rate at an even higher reading accuracy.
• Vehicle classification functionality added.
• Plate_finished field added to License_plate structure.
• Average frame rate fields added to LPR_Result structure.
• Reading rate improvements for UAE and New Zealand.
• Optimizations in memory handling and parallelization pipeline.
• Best mode added (even better than best).
• Reading improvements for 2-rows plates - mainly Germany.
• Recognition of Swiss cantons added.
• Reading quality improvements for stacked characters.

WebGUI

The Web GUI of CARRIDA has received several enhancements:

• Design improvements of interface elements and layout.
• The download of log files now loads all log files, including the log files which are part of the log rotation process (file.log.1, file.log.2, etc.).
• Added Possibility to enable/disable SSL as well as upload a new SSL certificate and key to the camera.
• The HTTP server listens on the port 80 and automatically redirects to HTTPS if SSL is used in web UI.
• Show status or bash output while installing SW update via UI.
• Add separate flags for import of actions and lists.
• An editor for the low level configuration has been added. This can only be opened by the camera SuperUser.
• The Web GUI is now logging all user actions in GUI.
• Added new min/max/avg character height of detected plates info in live view.
• Added new Count of correct/wrong direction readings info in live view.
• Added new Heatmap display of license plate detections as overlay on the live view.
• Improve visualization of Accepted Character Height graphic in Settings. Make the graphic interactive so that user can change minimum and maximum accepted character height parameters directly in the visualization.
• Display processing frame-rate for the last 1, 10 seconds, and since last reboot.

REST API

• Added ROI to the overview camera parameter.

A list of abbreviations used throughout this document

ANPR

Automatic License Plate Reader.

ARM64

Stands for processors with the v8 AARCH 64-bit instruction set.

ARM

Stands for processors with the v7 ARM 32-bit instruction set.

dB

Decibel, used to describe a relative sensitivity (gain) value in cameras.

fps

Frames per second.

FOV

Field of view.

HW

Hardware.

LP

License Plate.

mA

Milli-Ampere, one 1/1000 ^th of an ampere.

ms

Millisecond, one 1/1000 ^th of a second.

PC

Personal Computer.

PK

Product Key (for software licensing).

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. 32-bit hardware.

x86_64

Stands for Processor Architectures with the Intel instruction set. 64-bit hardware.

VC

Vision Components GmbH.

OSD

On-screen display

Image symbols used in this document

Symbol	Meaning
	Points to especially important aspects of the manual or the software.
	The lightbulb highlights the hints and the ideas that may be helpful.
	This warning sign alerts of possible pitfalls to avoid. Please pay careful attention to sections marked with this sign.