Sony to Start its AI-Processing Sensor Trials in Rome

Sony Europe announces its IMX500 sensors with AI processing functionality are at the core of three smart city trials being run by Envision in the municipality of Rome. These are intended to cut the city’s transport-related pollution and accidents at pedestrian crossings. 

The trial’s primary objective is to evaluate and deliver a smart parking system using IMX500 to reduce pollution and gridlock from those cruising to find a parking space. For this, the trial seeks to evaluate the effectiveness of such a system, with drivers alerted via a smartphone app before being directed to the free parking space closest to the driver’s destination. 

In addition to this, the test also includes a study of smart city systems that will optimise capacity and increase the use of its public transport network by implementing smart bus shelters, counting those getting on and off each bus – identifying overloading to ensure better provisioning of buses and costs optimization. 

Finally, an alert system at pedestrian crossings will be progressively activated to alert drivers when pedestrians are crossing, using low-latency smart lighting on the road to make them more visible with the aim of reducing the city’s accidents on pedestrian crossings.

The trial is set to commence in early June. 

The IMX500 used for this trial allows to extract real time metadata related to information of a free parking space, the presence of a pedestrian about to cross a street, or the number of people getting on / off a bus. No images are stored, nor leave the sensor, in line with privacy requirements. 

Sony Europe is committed to supporting the development and implementation of smart city projects with a view to help cities to solve their different issues through a Sensing as a Service (SeaaS) business model.

The average distance between pedestrians and vehicles is a key metric used to measure pedestrian safety. The trial is aiming to deliver a quantitative analysis of this and prevent pedestrian accidents through signalling mechanisms installed at the crossings.

Genius version smart tips have been installed on top of some traffic lights in Rome’s city centre. A preliminary phase was undertaken to train a neural network to identify available parking spaces as well as the number of people waiting at the bus stops, entering / leaving the bus and waiting to cross or crossing the road.

Every Genius smart tip consists of two sensors looking over the roads around and the parking spaces. The sensors send real-time data elaborated by neural networks on the exact location of a free space, the pedestrians’ presence and the number of people queuing at bus shelters.

 The exact location of the free parking space data is streamed in real time through the smart tip. The data is then immediately processed by the sensor integrated in the smart tip, using neural networks, and the sent to the cloud software platform of the partner company, Envision. The coordinates of the free parking space’s location are overlaid in real-time on a map that is displayed on a mobile device used by the driver who is heading towards the area.

Pedestrians’ presence is measured and compared across different locations. The neural network system detects pedestrians at the zebra crossing and a lighting signal is sent to the drivers to alert them. 

Data of queue length and people getting on and off the bus are processed by the sensor in the smart tip through the neural network and sent to the Envision software platform which aggregates them and make them available to personnel managing the public bus network in order to enhance the planning and scheduling of the bus transportation network. A “crowded” figure of merit is provided to signal when the bus is running at over capacity to avoid overcrowded buses, better manage the transportation network and improve citizens’ journey experience. 

The trial is conducted in the City of Rome collaboratively by a number of start-up companies in the Italian ecosystem and with the support of Sony Europe.