noun_Email_707352 Breadcrumb arrow noun_917542_cc noun_Globe_1168332 Map point Play Untitled Retweet

The City of Helsinki pilots solutions for real-time traffic planning and control and open data provision

A system to collect, analyse and visualise video material for the City Planning Department using mobile cameras for real-time forecasting of traffic and offering services to city residents.

Tieto Corporation

Keilalahdentie 2-4 FI-02150 Espoo Finland

The City of Helsinki wanted a real-time view of traffic using multiple data sources.

A real-time view of traffic gives a graphic representation of data related to traffic, lanes, the locations of means of transport and conditions. It can provide short-term forecasts of traffic volumes, the flow of traffic, incidents, punctuality and prevailing conditions.

We built the system for the pilot project, supplied the equipment and developed a video analysis solution in collaboration with Tampere University of Technology.

Why is a real-time view of traffic needed?

Two main purposes were identified for traffic video analysis:

  1. Analysis of historical data to support planning and decision making (data collected in non-real-time over a longer period)
  2. Analysis of real-time data to obtain an accurate view of local incidents

Situation data based on a real-time view plays a central role in improving the smoothness and predictability of daily journeys and transportation, as well as traffic safety. Data can be transmitted to end users, service providers and others who can benefit from it.

Traffic data collected over a longer period can be used to create traffic flow forecasts and explore the effects of various incidents compared with the normal situation. Examples of incidents are traffic jams caused by major public events and accidents, as well as poor weather conditions. Forecasts help in effectively guiding traffic immediately after an incident and preparing for the consequences.

Real-time analysis of traffic data also helps deliver better services for city residents. Data on vacant parking spaces can be distributed to motorists using the system. Video material also reveals when it's time to clear snow from bicycle and pedestrian paths.

The goal: cost-effective data collection and analysis

Since a large number of mobile video recording units were needed to get a reliable and comprehensive real-time view, the system was designed using as inexpensive equipment as possible.

Low-cost Android phones were selected as cameras and attached to vehicle windscreens. Mobile phones come with sufficiently high quality cameras and built-in GPS tracking, making it easy to synchronise images with locations.

Phone sensors also provide data on acceleration, deceleration, vibration and other environmental factors that influence the usability of data. Off-the-shelf software is available and customisation is easy.

It is expected that the investment costs of the pilot will be recovered through the reduced cost of accidents, congestion and emissions, as well as new business operations. Having a real-time view makes it possible to address incidents through rapid identification, positioning and forecasting.

Lessons learned form 60,000 observations

The pilot generated some 60,000 observations. The system identified and classified passenger cars with an accuracy of up to 95 percent. Identification of other objects was lower.

To be useful in practice, the video analysis models need to be further developed. Analytics can be trained to increase the accuracy of the results and expand the solution’s potential uses.

Today’s technology is not yet mature enough for real-time video analysis of big data. The main reasons for this are data transfer challenges (4G networks have insufficient capacity, so 5G networks are a must) and large data processing needs. If the real-time requirements are sacrificed, the solution is feasible as is.

Data transfer would not be a problem if analysis could be performed by the recording device. If this was the case, it would not be necessary to transfer all video material for analysis - it would be enough to transfer the metadata, which requires much less capacity.

The City of Helsinki is piloting solutions for more real-time traffic planning with Tieto

 

The future looks bright with data

The trial was unique in that data produced by mobile cameras has not been used much to date. There were some flaws during the pilot phase – which was to be expected – but the results were interesting and quite encouraging, considering practical applications. The project provided valuable information on how video image interpretation methods work and how suitable existing video recording systems are for producing traffic data.

From the perspective of further development, the availability, quality and analysis of data can be improved in several ways:

  1. With sufficient incentives it may be possible to crowdsource data collection – i.e. involve motorists in collecting data for analysis – by offering cameras with video analysis capabilities for private cars.
  2. The number of static cameras at critical spots could be increased to help collect useful data.
  3. Cameras could be installed on public transport to generate traffic data across the entire route network.
  4. External data sources, such as accident data from emergency response centres, could be connected to the system to improve predictability and accuracy.
  5. As the data-processing capacity of smartphones increases and the 5G data transfer system evolves, it will become possible to spread analytics over the entire ecosystem and better meet the real-time requirements.

We will continue to work with the City of Helsinki to look into new technologies and opportunities to leverage data with the aim of providing better services for city residents

Share on Facebook Tweet Share on LinkedIn