FLOW Insights lets you build analytics to select only the trajectories you're looking for. When you're done building, it's time to get coherent traffic data about what interests you. Sinks let you receive the data in your own application, but FLOW Insights is perfectly capable of visualizing and presenting the data to you by itself thanks to widgets.

Widgets visualize some aspect of traffic objects selected by the operator they are attached to. Select the Widgets tab in the Programming elements menu to see all their available types.

The type of widget determines how it visualizes data. However, the attribute you set it to determines what it visualizes. Attributes are internal values that all operators keep track of, like the average speed of all selected trajectories. To demonstrate this, let's drag a Statistical value widget onto an operator.

After dropping, a dialog window opens where you can choose the attribute. Then select Apply settings. (You can reopen the window at any time by double-clicking the widget.) 

Select the Dashboard in the left menu. The dashboard displays all widgets in a tile-like layout. You can drag and rearrange them as you like. The Statistical value widget displays statistical data like maximum, minimum, and average value related to the attribute you selected for it, but only for the trajectories selected by the operator, it's attached to.

You can drag the widget by its header to a position that suits you.

All widgets provide you with time mode options. See Working with time in FLOW for more information about them.

Widget types

Value

Displays a single value.

Available attributes:

  • Object count - the number of trajectories selected by the operator

Statistical value

Displays a maximum, minimum, average, and median values for the chosen attribute. Select the statistical value in the bottom menu to control which of them is visualized by the middle bar.

Available attributes:

  • Speed - speed data of selected trajectories. 

  • Acceleration - acceleration data of selected trajectories. 

  • Stationary time - data about how long the selected traffic objects have had zero velocity while in the scene. 

  • Time of passage - data about how long the selected traffic objects have been in the scene.

Table

Displays a table of multiple records.

Available attributes:

  • Trajectory list - detailed information about each selected trajectory. 

You can export an excel file of the table with up to 100 pages of data. The time format you will get for the trajectories is UNIX time. How to convert UNIX time in ms format (1.1.1970) to a more understandable format?

Equation : X=((A1+3600000)/86400000)+DATE (1970;1;1)

A1=Unix Time in ms that we want to convert +3600000 (number of ms in one hour), this is included to add one hour – FLOW by default shows a different time - your PC´s time. This is not the time in which the unit is installed meaning the widget data is different to the data from the export.

The excel export gives you a UTC time format. To get the correct format you need to account for this and use: 3600000x(difference in the number of hours) and based on the time zone either add or subtract these hours from the exported time value.

For time zone +2 we would add 3600000x2 = +7200000. The goal of this is to adjust the time from my PC´s timezone to the timezone of the unit.

(1970;1;1) is UNIX time, time which serves as an anchor point for time-based data to which we add the value we get by diving A1+time zone adjustment by 86400000 which is number of ms in one day.

You should also set your cell format to hh:mm:ss for the English version of the excel to see the result in the correct format. For example, by converting 1605250440905 we will get the following date - 13.11.2020. 07:54:01.

Heatmap

Video view overlaid with a representation of a cumulated value for each pixel. The value is determined by the chosen attribute. Based on the selected color scheme, high values appear in hot or more intensive colors and low values in cold or less intensive.

Available attributes:

  • Speed map - how high the selected traffic objects' speed was on each pixel of the scene

  • Acceleration map - how high the selected traffic objects' acceleration was on each pixel of the scene

  • Occupancy map - how much time traffic objects spend on each pixel of the scene

Other settings:

  • Heatmap type - whether the widget is a heatmap or a grid map. The gridmap is explained further.

  • Color map type - the color scheme that represents the various values

  • Value range - which values should be colored as the lowest and highest. The adaptive mode determines this automatically from available data, in manual mode you can set the values yourself.

  • Opacity - how transparent the heatmap is. 0 is completely transparent, 1 is not transparent.

  • Dispersion radius - how much the data is "blurred" over neighboring pixels

  • Time mode options - see the related article for more information

Gridmap

A subtype of heatmap that groups the pixels of the original image into squares of certain size and colors the squares based on the selected statistical value computed over original pixels in the squares: Minimum, maximum, average, and median.

You can also set the square (tile) size or make the squares display the values inside them. Here's a closeup of the gridmap with values displayed.

Trajectory view

Displays a visualization of selected trajectories overlaid over a current video snapshot. The color of the trajectories corresponds to their category.

Available attributes:

  • Trajectory view

Distribution histogram

Displays a histogram of the chosen distribution. 

Available attributes:

  • Category distribution

  • Color distribution 

What next?

Find out about widgets' time modes, the possibility to view their history in charts and combine them into superwidgets, and how to use FLOW’s REST API and receive trajectory data in real-time into your own devices with sinks.

We will be happy to answer any questions you may have. Contact us!

Did this answer your question?