Set-up Traffic Counting
How to succeed in traffic counting including the classification of vehicles according to our Classes/Subclasses on dedicated urban & highway streets
You want to know the traffic situation of an urban street or highway? SWARM software is providing the solution to get the number of vehicles passing at the street split per vehicle type (Classes) and direction.
For this use case, SWARM software is providing you with any data needed for traffic counting - The counts of vehicles including classification can be covered. The counts are split between two directions (IN/OUT). Furthermore, several counts can be made in one video camera, e.g.: count each lane separately. On top, you have the opportunity to add a second counting line, calibrate the distance in between and estimate the speed of the vehicles passing both lines.
Camera Set-up
How to configure?
How to get the data?
Find detailed information about camera requirements/settings as well as camera positioning in the table below.
| Recommended |
Pixels Per Meter is a measurement used to define the amount of potential image detail that a camera offers at a given distance. | > 30 PPM (vehicle) > 60 PPM (rider, person) Using the camera parameters defined below ensures to achieve the minimum required PPM value) |
Camera video resolution | 1280×720 pixel |
Camera video protocol/codec | RTSP/H264 |
Camera Focal Length | 2.8mm |
Camera mounting - distance to object center | 5-30 meters (vehicle) 5-15 meters (rider, person) |
Camera mounting height | 3-6 meters |
Camera mounting - vertical angle to the object | <50° Note: setting the correct distance to vehicle and camera mounting height should result in the correct vertical angle to the vehicle |
Camera mounting - horizontal angle to the object
| 0° - 90° |
Wide Dynamic Range | Can be enabled |
| |
Camera | | Link | Comment |
HikVision | Dome Camera DS-2CD2046G2-IU | 2,8 mm Focal Length |
The configuration of the solution can be managed centrally in SWARM Control Center. Below, you can see how a standard traffic counting 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 |
|---|---|
Model | Traffic & Parking |
Configuration option | Counting Line (optional speed) |
ANPR | Disabled |
Raw Tracks | Disabled |
For receiving the best accuracy of the counting including the classification, the Counting Line should be placed approx. in the middle of the video frame so that vehicles from both directions are seen long enough for good detection and classification.
You can choose the direction IN/OUT as you want in order to retrieve the data as needed.
In our Traffic Scenario section, you can find more details about the possible Widgets to be created in the Traffic Scenario Dashboards.
Here is an example for a Traffic counting widget You have the different options to choose the data you want for a certain time period as well as choosing the output format (e.g.: bar chart, table, ...).
Traffic Counting Widget
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 in Excel.
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
Object velocity | < 130 km/h |
Day/Night/Lighting | Daytime/Well illuminated/Night vision |
Indoor/Outdoor | Outdoor |
Expected Accuracy (Counting+Classification) (when all environmental, hardware, and camera requirements are met) | Counting >95% (vehicles, bicycles)
Classification of main classes: >95%
Classification of subclasses: >85% |
| |
Supported Products | VPX, P100/OP100/StarterKit |
Frames Per Second | 25 |