Technical Documentation
Version 2023.1
Search
⌃K

Set-up Barrierless Parking with ANPR

How to succeed in setting up an Entry/Exit parking system with ANPR
You have a parking space where you want to know your utilization and parking times of your customers, then you can use the SWARM solution as following.

What data can be generated?

For this use case, SWARM software is providing you with any relevant data for your Entry/Exit parking space. The solution is gathering the number of vehicles in your parking space as well as the number of vehicles entering and exiting your parking space for customizable time frames.
The vehicles are classified in any classes the SWARM software can detect. Nevertheless, consider that the following configuration set-up is optimized to detect vehicles and not people and bicycles.
Thanks to the License plate recognition, the parking duration of your customers will be analyzed. On top of the License plate information as well, the license plate origin country is available as meta information. The country codes are according to ISO 3166 Alpha 2 standard. The country classification is working with excellent accuracy of 99%.

What needs to be considered for a successful analysis?

Find below some general settings for the installation of this use case. As the automatic number plate reading needs some more detailed information you will find additional and more detailed information on how to set it up in the following page:
Camera Set-up
How to configure the solution?
How to get the data?
Especially for Automatic Number Plate Recognition (ANPR) the camera choice and positioning are essential.
The requirements for accurate number plate recognition can be aligned with respective norms for the accurate operation of (human-based) surveillance systems.
The standards give a recommended pixel-per-meter measure (“pixels on target”), to reliably perform that task (by a human). The relevant category for clear reading of license plates/identification of a person “without a reasonable doubt” is “identify”. A Bullet camera is recommended.
Text
Recommended
Pixels Per Meter is a measurement used to define the amount of potential image detail that a camera offers at a given distance.
> 250 PPM
To clearly read a license plate, at least 250 PPM are required. Using the camera parameters defined below ensures to achieve the minimum required PPM value)
Resolution
min. 1920 × 1080 (H264)
Focal Lenght
min 3.6-8 mm motorized adjustable focal length recommended
Mounting
Distance and height of installation
Note: setting correct distance to license plate and camera mounting height should result in the correct vertical angle to license plate Horizontal angle to license plate
Exposure / Shutter speed
max. 1/250 for objects not moving faster than 40 km/h

Possible Camera for this use case

Manufacturer
Model
Link
Note
Hikvision
Bullet Camera
DS-2CD2645FWD-IZS
Motorized varifocal lens
The configuration of the solution can be managed centrally in SWARM Control Center. Below, you can see how the Entry/Exit parking with license plate detection needs to be configured for optimal results.
In order to start your configuration, take care that you have configured your camera and data configuration.

Configuration settings

Configuration
Model
Traffic & Parking
Configuration option
CL (Counting Line)
ANPR
Enabled
Raw tracks
Disabled

How to place the configuration type?

For receiving the utilization of your parking space including the park durations of your customers, a CL for each Entry/Exit needs to be configured. The CL should be placed approx at the beginning from last third of the frame in order that the object can be over several frames, so that the License plate detection and classification are most accurate.
Consider that the IN/OUT direction of the crossing line is important as it is relevant for calculation of the park duration. (IN = Entry to parking, OUT = Exit of parking).

Visualize data

You can visualize data via Data Analytics in different widgets.

Scenario

In our Parking Scenario section, you can find more details about the possible Widgets to be created in the Parking Scenario Dashboards.

Example

You are able to visualize the data for any Entry/Exit you have configured with the Counting lines. So you are able to see the number of vehicles with their classes/subclasses and license plates of any Entry or Exit.
Furthermore, you will be able to gather a list of customers with the corresponding license plate that has parked longer than your preconfigured parking duration is. For the purpose of provability, you can also see a picture of the incoming and outgoing vehicle. Please mind that you need to configure the parking time due to your data privacy restriction.
Parking time violations

Retrieve your data

If you need your data for further local analysis, you have the option to export the data of any created widget as csv file for further processing.
csv. export
If you would like to integrate the data in your IT environment, you can use the API. In Data Analytics, you will find a description of the Request to use for retrieving the data of each widget.
REST API
In case you are using your custom MQTT broker, you can also retreive the raw data there. We provide a special option to have the license plate capture added to the event schema. This enables you to retrieve the capture within the pushed MQTT message. The picture is encoded in BASE64. In order to enable this option, please contact our support.

Environment requirements

European countries
Examples:
Licence plate types
‘standard’ car license plates (520 by 120/110 mm)
Note: square two line license plates (e.g. motorbike) are not supported
Object velocity
<= 40km/h with low-light conditions
Area of focus
Single lane when camera mounted on the side; Two lanes when mounted above the center of both lanes
Day/Night/Lighting
Daytime or well illuminated only (min 500 lux)
Indoor/Outdoor
Indoor & Outdoor
Expected Accuracy (Counting + License Plate)
(when all environmental, hardware and camera requirements met)
>90% Only vehicles are considered. For parking spaces people, bicycles and motorbikes are not part of our test scenarios as they don't occupy parking spaces.

Hardware specification

The License plate recognition is not supported on the P100 SWARM Perception boxes. So for this use-case, the new P101 SWARM Perception box or a VPX deployment option with NVIDIA-based hardware is needed.