Sony Europe has announced its IMX500 image sensors with AI processing functionality are at the heart of three smart city trials to be conducted with Envision in the municipality of Rome, Italy, starting in June. These aim to reduce pollution linked to city transport and accidents at pedestrian crossings.
The main objective of the trial is to evaluate and deliver an intelligent parking system using IMX500 to reduce pollution and traffic jams for those who travel to find a parking space. For this, the test seeks to assess the effectiveness of such a system, drivers being alerted via a smartphone application 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 optimize the capacity and increase the use of its public transport network by setting up smart bus shelters, including those that go up. and get off each bus – identifying overloads to ensure better bus supply and cost optimization.
Finally, a zebra crossing alert system will be gradually activated to alert drivers when pedestrians cross, using smart low-latency lighting on the road to make them more visible with the aim of reducing city crashes on roads. pedestrian crossings.
The IMX500 is the first image sensor to incorporate AI processing functionality. The configuration used for this test makes it possible to extract real-time metadata related to information about a free parking space, the presence of a pedestrian about to cross a street, or the number of people getting on / off a street. ‘a bus. No image is stored, nor leaves the sensor, in accordance with privacy requirements.
This allows the city to reduce the required bandwidth, easily scale it up using existing networks, and lower electricity and communication costs. In addition, this system makes it possible to respond to citizens’ concerns in terms of confidentiality.
Sony Europe is committed to supporting the development and implementation of smart city projects to help cities solve their various problems through a Sensing as a Service (SeaaS) business model.
Problems of large cities: traffic, traffic jams and pedestrian safety
Traffic caused by those looking to park is seen by the city as a key driver of congestion, with the essay seeking to quantify the extent of the problem. Using Sony’s imaging and sensing technology to serve social causes in cities shows how IMX500 sensors can alleviate some of the problems faced by busy cities.
The average distance between pedestrians and vehicles is a key metric used to measure pedestrian safety. The test aims to provide a quantitative analysis and to prevent pedestrian accidents using signaling devices installed at level crossings.
Antonio Avitabile, Managing Director of Corporate Alliance and Investment at Sony, comments: “This is a clear and concrete example where Sony’s intelligent vision solution can serve the purpose of our customers while respecting the privacy of customers. people.
“Our vision is to create more sustainable and livable cities, and with the scalable IMX500 platform, we can dramatically accelerate this process. “
The technology used
Genius version smart tips have been installed in downtown Rome. A preliminary phase has been undertaken to train a neural network to identify available parking spaces as well as the number of people waiting at bus stops, entering / exiting the bus and waiting to cross or cross the road.
Each Genius smart tip consists of two sensors that monitor surrounding roads and parking spaces. The sensors send real-time data compiled by neural networks on the exact location of an open space, the presence of pedestrians and the number of people queuing at bus shelters.
The exact location of the free parking space data is broadcast in real time using the smart trick. The data is then immediately processed by the sensor integrated into the smart tip, using neural networks, and sent to the partner company’s cloud software platform, Envision. The coordinates of the location of the free parking space are overlaid in real time on a map that is displayed on a mobile device used by the driver on their way to the area.
The presence of pedestrians is measured and compared at different locations. The neural network system detects pedestrians at the zebra crossing and a light signal is sent to the drivers to alert them.
Smart bus shelters
Data on queue length and people getting on and off the bus is processed by the smart tip sensor through the neural network and sent to the Envision software platform, which aggregates and updates it. the provision of staff managing the public bus network to improve the planning and scheduling of the bus transport network. An “overcrowded” merit figure is provided to signal when the bus is operating at full capacity in order to avoid overcrowded buses, better manage the transportation network, and improve the commuting experience for citizens.
The trial is being carried out in the city of Rome in collaboration by a number of start-ups from the Italian ecosystem and with the support of Sony Europe.