RSS
Логотип
Баннер в шапке 1
Баннер в шапке 2

PNIPU: Intelligent building image processing system

Product
The name of the base system (platform): Artificial intelligence (AI, Artificial intelligence, AI)
Developers: PNIPU Perm National Research Polytechnic University
Date of the premiere of the system: 2021/07/29
Branches: Real estate,  Construction and construction materials industry
Technology: BIM - Information modeling of buildings and structures,  Video analytics systems

Main article: Machine learning

2021: Intelligent Building Image System Development

On July 29, 2021, Perm Politech announced that its researchers had trained artificial intelligence to recognize the image of the city.

A young researcher from Perm Polytechnic has developed an intelligent system for processing images of buildings, which can determine the color patterns of architectural objects. The technology will help developers of apartment buildings more effectively integrate projects into urban space.

Artificial intelligence and machine learning technologies are actively introducing into architecture and urban planning. They help optimize planning solutions, engineering systems, as well as provide safe and comfortable living conditions for people.

File:Aquote1.png
We trained the system using digital images of buildings. Intellectual analysis helped to find out what colors are characteristic of certain cities, and to establish which settlements are similar to each other. The development allows you to determine from the photograph of the residential complex to which city it belongs, "explains Olga Bolotova, a graduate of the construction faculty of Perm Polytechnic.
File:Aquote2.png

The objects of the study were apartment buildings in the largest Russian million-plus cities. The intelligent solution will become a recommendation system for architects and specialists in related fields. According to the developers, in the creative process of searching for the color design of the building, a person cannot be replaced, but the system will be able to become his digital assistant.

Researchers analyzed 15 images of residential complexes under construction in Perm that did not participate in the training of the program. The system determined that all houses are new buildings, and the complexes are similar to Perm. Development identified 13 buildings as Perm, and two residential complexes according to the analysis turned out to be similar to other cities: Yekaterinburg and Omsk. For one of them, the developer identified the most relevant colors in Perm and proposed options for changing the facades.

File:Aquote1.png
The software solution can be used by developers to audit sketched solutions. The system will help to give recommendations on the design of buildings so that they meet their goals as much as possible and are harmoniously embedded in the city space, "explains Irina Alekseeva, project manager, associate professor of construction engineering and materials science at Perm Polytechnic, candidate of economic sciences.
File:Aquote2.png

To create the development, in particular, for spectral analysis of images and identification of parameters of information models, researchers used domestic software.

The system of Olga Bolotova has already received high praise from the Department of Urban Planning and Architecture of the Perm Administration. The developers plan to create similar solutions for buildings of general education and preschool educational organizations, fitness complexes, pools and other public buildings, as well as to study color patterns in the urban environment to check the unity of design of buildings in one territory. Researchers are engaged in these areas on the recommendation of the chief architect of the city Dmitry Lapshin.