The system for monitoring the improvement and maintenance of urban areas is a tool that helps operators of the Center for Automatic Recording of Administrative Offenses to monitor cleanliness in the city and receive information about irregularities.
Neural networks analyze screenshots from cameras and detect irregularities in each of them. 20 video analytical modules are implemented in the system. The modules detect piles of snow, overflowing garbage bins, dirty road signs and potholes. In the future, the neural network will be able to control the removal of snow from roofs. Also, six video-analytical modules have been developed for employees of the State Real Estate Inspectorate. These modules help to detect summer cafes, construction sites, littering of sites with construction waste.
The operators of the Center for Automatic Recording of Administrative Offenses check only those screenshots, in which cameras have detected violations. This saves time for employees and helps to reduce response time.
Now the neural network analyzes more than 1 million images from CCTV cameras every month.
#smartcitymoscow
the most important news on urban digital technologies
Unless otherwise stated, the content is available under Creative Commons BY 4.0 license
Supported by the Moscow Government
Content and Editorial:tech@ict.moscow