Cities are full of camera’s. Security camera’s in shops and government building. camera’s for traffic control, etcetera. Nowadays most of these camera’s are connected to the internet, but they cannot communicate yet with each other. US technology firm Nvidia wants to change that with the introduction of Metropolis, an all knowing video platform, based on artificial intelligence in combination with deep learning.
Metropolis is an intelligent video analytics platform that makes cities safer and smarter by applying deep learning to video streams for applications such as public safety, traffic management and resource optimization. The Metropolis platform enables cities to put AI behind every video stream to create smarter cities.
“Deep learning is enabling powerful intelligent video analytics that turn anonymized video into real-time valuable insights, enhancing safety and improving lives,” said Deepu Talla, vice president at NVIDIA.
Example: nowadays, if a fellony takes place, the police requests video footage of camera’s in the proximity of the verdict to see if they contain valuable information. The Metropolis system sets already an alarm at the time the fellony takes place. And even better, camera’s hold track of the offender and alarms the police about the his/her whereabouts.
Video Is World’s Largest Data Source
Video is the world’s largest generator of data, captured by hundreds of millions of cameras deployed in areas such as government property, public transit, commercial buildings and roadways. By 2020, the cumulative number of cameras is expected to rise to approximately 1 billion.
The Metropolis can analyze and interpret thirty billion images per second. Other examples are camera’s in drones, camera’s in robots inspecting sewer. Compare it with Lego blocks which, if connected with each other, will become the city of the future.
Nvidia’s goal is to have all public camera’s worldwide connected, expected to be around one billion in 2020.
Also for transportation and commercial industries
“The Metropolis platform can be applied to video streams to create smarter and safer applications for a variety of industries — from transportation to commercial,” said Shiliang Pu, president at Hikvision Research Institute.”
Traffic control can be optimized by alerting drivers about traffic jams or parking spaces, saving gas and preventing pollution. Traffic lights can be adjusted to congestion and car navigation systems can be connected as well.
Or think about instore marketing. Camera’s can, if the customer allows, recognize the customer to be able to get an extreme personalized customer experience.
See this video for more information.
*) Featured image: Frédéric Bisson (cc)