Set-up Journey Time & Traffic Flow

Detailed information on the solution for Journey time and area-wide traffic flow in terms of data generation, camera set up and Analytics options.

Next to the traffic frequency at given locations, you are wondering about statistics on how long the vehicles take from one to another location and how the traffic flows across your city and municipality. With this solution, you can generate that data with a single sensor solution from SWARM.

What data can be generated?

For this use case, SWARM software is providing you with the most relevant traffic insights - The counts of vehicles including the classification of the SWARM main classes can be covered. 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. By combining more sensors in different locations the journey time as well as the statistical traffic flow distribution will be generated.

The journey time and traffic flow distribution can be generated for vehicles only (car, bus and truck).

What needs to be considered for a successful analysis?

Camera Set-up

Find detailed information about camera requirements/settings as well as camera positioning in the table below.

Set up parameters	Recommended
Pixels per Meter (PPM) 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 (vehicle) Using the camera parameters defined below ensures achieving the minimum required PPM value) Tip: Use the Axis lens calculator or generic lens calculator.
Camera video resolution	1920x1080 pixel
Camera video protocol/codec	RTSP/H264
	USB 3.0/UYVY, YUY2, YVYU
Camera Focal Length	min. 3.612 mm motorized adjustable focal length
Camera mounting - distance to object center	5-20 meters Please consider that the zoom needs to be adjusted according to the capture distance. More details are in the installation set-up guide.
Camera mounting height	3-8 meters Please follow the installation set-up guide in detail.
Camera mounting - vertical angle to the object	<40° Note: setting the correct distance to vehicle and camera mounting height should result in the correct vertical angle to the vehicle More information in the Installation set-up guide.
Camera mounting - horizontal angle to the object	0° - 20°

Possible cameras for this use case

Camera		Link
Dahua	IPC_HFW5442EP-ZE-B	https://www.dahuasecurity.com/asset/upload/uploads/soft/20190506/DH-IPC-HFW5442E-ZE.pdf
HikVision	DS-2CD2646G2-IZS	https://www.hikvision.com/en/products/IP-Products/Network-Cameras/Pro-Series-EasyIP-/ds-2cd2646g2-izs/

How to configure?

The configuration of the solution can be managed centrally in SWARM Control Center. Below, you can see how the standard is configured for optimal results.

In order to start your configuration, take care that you have configured your camera and data configuration.

Configuration settings

Configuration	Settings
Model	Traffic & Parking (Standard)
Configuration option	Counting Line
Journey Time	Choose Journey time mode on Global settings
Raw Tracks	Disabled

What should be configured?

In order to retrieve the best accuracy we strongly recommend to configure a focus area on the maximum two lanes which should be covered for the use case.

❗Make sure to place focus areas in a way that it covers enough space before an event trigger so that the model is able to "see" the objects for a similar amount of time as if the focus area wasn't there. The model ignores all objects outside a focus area so there is no detection, no classification, no tracking and no ANPR reading conducted.

Think of focus areas as inverted privacy zones - the model only "sees" objects inside an area, the rest of the image is black.

In order to receive the counting data as well as the journey time data, a Counting Line needs to be configured as an event trigger.

How to place the event triggers?

For receiving the best accuracy of the counting including the Journey time information the Counting Line should be placed at a point where the vehicle and the plate will be seen for approx. 10m in distance. On top take care to configure the Counting line at a place where the track calibration still shows stable tracks.

You can choose the direction IN/OUT as you want in order to retrieve the data as needed. On top, you have the option to give a custom direction name for the IN and OUT direction

How to get the data?

Visualize data

You can visualize data via Data Analytics in different widgets.

Scenario

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

pageTraffic Scenario

Examples

Here is an example for a Journey time widget. Journey time can be shown as average, median or up to two different percentiles.

Journey Time (average and median) widget of two journeys.

Another example below that visualizes the journey distribution. There is a slidebar to go through the different time periods of the chosen aggregation level. On top the figures can be changed easily between absolute and relative values.

Journey distributions widget.

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 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

Environment specification

Object velocity	< 80 km/h
Day/Night/Lighting	Daytime/Well illuminated/Night vision
Indoor/Outdoor	Outdoor

Accuracy

In this technical documentation, accuracy refers to the penetration rate of a single sensor, which is the percentage of correctly identified license plates divided by the total number of vehicles counted during a ground truth count.

The current penetration rate for this use case is 60%, taking into account different day/nighttimes, weather conditions, and traffic situations. When calculating journey time between two sensors, approximately 36% of journeys are used as the baseline, which is calculated by multiplying the penetration rate of both sensors.

The accuracy is sufficient to generate data that can be used to make valid conclusions about vehicle traffic patterns and journey times.

Hardware Specifications

Supported Products	VPX, P401, P101/OP101
Frames Per Second	25