Definition of object classes for Traffic & Parking (Standard & Accuracy+)
The following images are only intended as examples and are not intended to provide information about exact camera distances or perspectives.
car
Car includes small to medium-sized cars up to SUVs, pickups and minivans e.g. VW Caddy, Renault Kangoo. This class does not include cars with trailers.
car
van
Vans are vehicles for transporting a larger number of people (between six and nine) e.g. VW Multivan, or are used for deliveries e.g. VW Transporter, Fiat Ducato.
Delivery vans with closed and open loading space are also included, e.g. Iveco Daily.
car
car with trailer
Cars and vans towing a trailer are considered car with trailer. For correct classification, the entire vehicle and at least one of the trailer's axles must be visible.
truck
single unit truck
Single unit trucks are vehicles defined as unit transporters with two or more axles. It is important for the definition that the towing vehicle and semi-trailer cannot be separated from each other.
truck
articulated truck
Articulated trucks are large vehicles with more than two axles in which the articulated truck and semi-trailer can be separated. An articulated truck without a semi-trailer is classified as a single unit truck.
truck with trailer
Single unit trucks or articulated trucks towing an additional trailer are defined as truck with trailer.
bus
-
A bus is a vehicle for transporting a large number of people. This includes coaches, double-decker buses, motor coaches, buses, passenger coaches and school buses.
motorbike
-
The motorbike class includes a person riding a motorized single-track vehicle. This also includes motorcycles with sidecars; e-bikes are not included in this class. Motorcycles without a rider are not taken into account.
bicycle
-
The class bicycle includes a person who actively rides a bicycle. Persons pushing a bicycle are not included in this class and are considered a person. Bicycles without a rider are not included.
person
-
The class person includes pedestrians: Inside as well as people who ride segways, skateboards, etc. ride. This class also includes people pushing a bicycle or baby carriage.
scooter
The class scooter includes a person riding a scooter that is either motorized or not. A scooter normally consists of two wheels and a handlebar.
tram
The class tram refers to a means of public transport that runs on rails along roads or dedicated streetcar routes. Streetcars are usually electrically powered and draw their electricity from overhead lines.
other
-
Vehicles or objects that do not correspond to the above classes fall into the other class. This applies to tractors (with or without trailers), ATVs and quads, forklifts, road rollers, excavators and snow plows.
Here you will find information on how to successfully connect and configure the camera.
To call up the configuration page of the devices, simply click on the respective device in the “Devices” list view. You can use this to manage all cameras that are processed on this device.
We recommend a logical naming scheme for the devices at this point.
Click on one of the cameras displayed to open the settings for the respective camera. As soon as you have configured the camera connection, you will see a preview of the camera image.
In the configuration, you can select the model suitable for your use case and configure event triggers. Please consult the corresponding section in the solution areas.
Below you will find a brief description of each model. Different models are recommended depending on the solution area.
Traffic & Parking (standard): Recognition of 12+1 object classes in the context of traffic and parking.
Traffic & Parking (Accuracy+): Recognition of 12+1 object classes in the context of traffic and parking. Optimized for higher accuracy at a processing speed of about half (measured in FPS) compared to “Traffic & Parking (Standard)”
See class definition for a detailed description of the classes.
The entire body of a person is recognized.
Note: When recognizing and tacking people, we do not perform facial recognition at any time. No sensitive personal information is processed.
The head of a person is detected. This is advantageous if the entire body is not visible and the distance to the objects is less than 5 meters.
Note: When recognizing and tacking people, we do not perform facial recognition at any time. No sensitive personal information is processed.
Event triggers trigger an event when a defined condition is met.
Counting lines (CL) trigger a count as soon as the center of an object crosses the line. When configuring a CL, it is important that the camera perspective is taken into account.
The CL also logs the direction in which the object has crossed the line in the In and Out direction. You can swap the In and Out direction at any time. In addition, a separate name can be assigned for the two directions.
By default, a CL only counts each object once. If every crossing is to be counted, there is an option to activate events for repeated CL crossings. With the restriction that counts are only taken into account if there are five seconds in between.
In addition to the repeated CL crossings, ANPR and Speed Estimation are also available as triggers or settings.
Speed Estimation_ can be activated as a special trigger setting for a CL in the left sidebar. This adds another line that you can use to specify the distance in your scenario. For the best results, we recommend a straight line without curves/slopes.
Regions of Interest** count objects in a specific area.** In addition, the class (Class) and dwell time (Dwell Time) are determined and specified.
Depending on the scenario, we can distinguish between three types of RoI. We offer the templates described below for these three types:
Event- Trigger
Duration (Time)
Duration (Time)
Duration (Time) or Status (Occupancy)
Event- Type
Parking
Parking
People and Traffic
Number of preset Objects
1
5
1
Color
dark green
purple
light green
These zones are used for origin-destination analyses. Counts are generated when an object moves through OD1 and then OD2. At least two areas must be configured for an OD.
The first zone that the object passes through is called the origin zone (Origin). The last zone that the object passes is therefore referred to as the destination zone (Destination).
Your devices send events to an MQTT broker when a trigger is triggered. The standard configuration sends data to the data center. Custom-MQTT allows you to send events to an MQTT broker provided by you, the definition of the event format can be found here.
Message compression can save up to 50% bandwidth used to send events to the MQTT broker. Please note that the broker and application must support decompression of zlib / inflate.
