Vision Path Tracing

Vision Path Tracing

Tracsis launched our Path product in 2019, powered by the Felicity platform from Vivacity. This innovation adds enhanced visualisation and insights to our powerful video analysis tools for clients across the transport industry.

The insights include:

Visual turning proportionality

Road space utilisation

Pedestrian and cyclist desire lines

Pedestrian crossing usage

As an enhancement to traditional video footage analysis Tracsis is able to offer a unique path tracing service, offering users a highly customisable way of visualising the volume of vehicle and pedestrian traffic captured during any video survey work.

Using a proprietary machine-learning system, objects passing through each camera’s field of vision are classified into one of nine categories and their routes are shown via the medium of trace lines overlaid onto a background image from the relevant camera.

The system is highly flexible, with traces for each camera available to view for time increments of anywhere between 1 minute to the full duration of the video file, while also allowing for the results of individual classifications to be toggled on or off by the user.

This functionality can be applied to any video survey undertaken by Tracsis to provide valuable insight into traffic behaviour.

We recommend that you allow a period of 7 working days from completion of the relevant survey, though times may vary depending on the volume of analysis being run through the system.

Customers are provided access to the video trace portal once their trace data is available.  In order to enable access, Tracsis will require the email addresses for up to 3 users from the customer’s team.

Object data is classified into one of the following categories: Pedestrian, Pedal Cycle, Motorcycle, Car, Taxi (Hackney), LGV, OGV1, OGV2, Public Service Vehicle (Bus).

Path traces will be available for the entire duration of a survey day, with each day being separated into video segments of an hour.  Traces cannot currently be viewed across multiple hours, though we are hoping to include this feature in a future update.

The system typically achieves in excess of 90% accuracy when classifying objects.  Our technicians are trained in effectively installing cameras to achieve optimal results using this technology. Note however that accuracy can be impacted in the event that the camera view is obscured or impaired.

What our clients say…

“Peter Brett Associates (Stantec) are regularly involved in commissions focusing on urban realm, regeneration, placemaking and active travel. The Tracsis Path tracing software allows us to collate a wide range of statistical and visual information, providing a strong evidence base to our clients and funding partners. 

The flexibility provided in the analysis is particularly helpful in terms of presenting findings to our clients. The online portal is user-friendly and Tracsis are always on hand for technical support. We will be using this technology for future projects and studies.”

Peter Brett Associates


“We used Path* from Tracsis outputs to help inform a study into pedestrian crossing behaviour – allowing us to identify the main desire lines at each site, and where people most commonly deviated from these. This provided an insight into the dynamics of each specific site and helped us to develop theories for why this might be.

Ultimately, the Path traces were a key part of the puzzle in terms of identifying where people’s crossing behaviour needed to be influenced. Being able to compare between different periods of the day was particularly important to understanding the changing dynamics of the site.”

* Path products are powered by the Felicity platform from Vivacity.

Geoff Burrage, Associate Director
Integrated Transport Planning Ltd

View the Demonstrator

Login for free to see our Path Tracing demonstrator software

Samples from real survey data visualised with Tracsis Path Tracing: