{"id":13446,"date":"2024-02-26T00:04:17","date_gmt":"2024-02-25T22:04:17","guid":{"rendered":"https:\/\/clients.triloogia.ee\/proekspert\/wp-new\/?post_type=case-study&p=13446"},"modified":"2025-01-07T11:30:11","modified_gmt":"2025-01-07T09:30:11","slug":"software-to-identify-football-fields","status":"publish","type":"case-study","link":"https:\/\/clients.triloogia.ee\/proekspert\/wp-new\/case-studies\/software-to-identify-football-fields\/","title":{"rendered":"Software to identify football fields and their surface material using ESA satellite imagery"},"content":{"rendered":"\n
\n
\"\"<\/figure>\n<\/div><\/div>\n\n\n\n
\n
\n
\n

Client challenge<\/h3>\n\n\n\n

Investigate whether it is technically and commercially feasible to use machine learning to obtain information about the location and composition of football fields.<\/p>\n<\/div>\n\n\n\n

\n

Technologies<\/h3>\n\n\n\n

U-net, OpenCV, Postgres, CouchDB<\/p>\n<\/div>\n\n\n\n

\n

Project duration<\/h3>\n\n\n\n

2,100 man-hours, 1+ years<\/p>\n<\/div>\n<\/div>\n<\/div><\/section>\n\n\n\n

\n
\n
\n

Solution at a glance<\/h2>\n\n\n\n

We built an application to select areas of interest, obtain a list of football fields, and view the results using a map application. A distinction is made between fields covered with natural grass and artificial turf. <\/p>\n\n\n\n

The service uses satellite images, which are analyzed with the help of machine learning algorithms with the purpose of obtaining a list of identified fields covered with artificial or natural turf. A user interface enables access to the map application where the user selects a geographical spot of interest. By clicking on a map location, the customer activates the application to obtain images of that area. As a result of the analysis, the user will receive a list of links to football field locations on the map. The customer may click on the link and continue their investigation about that specific field. <\/p>\n\n\n\n

The application is designed to locate football fields and identify field material. Additional features may be added on request.  <\/p>\n\n\n\n

Our technology enables use of a wide variety of satellite images for football field detection and characterization.<\/p>\n\n\n\n

Project<\/h2>\n\n\n\n

The growing global population has increased the demand for open-air sports and leisure facilities like football- and rugby fields and public playgrounds. However, the costs to build and maintain these facilities are also increasing. As a cost-saving measure, more facilities with artificial turf are being built. <\/p>\n\n\n\n

Surfaces of artificial turf can have environmental impacts, and therefore they cannot be built everywhere. For example, black-rubber crumb fields, produced from discarded tires, may not be placed too close to bodies of water. Also, in warmer geographies, water is required to cool the rubber to protect the players, which must be weighed against the water required for natural grass. Satellite imagery can assist in making these decisions, as well as provide information about the condition of fields.<\/p>\n\n\n\n

To plan better investments and optimize maintenance costs, up-to-date information is needed about football fields and their condition. Currently, such information is not easily available or obtainable at a reasonable cost.<\/p>\n\n\n\n

Proekspert built an application that enables the selection of an area of interest for review, obtain a list of football fields in the area, and then view the results using a map application. The distinction is made between fields covered with natural grass and artificial turf.<\/p>\n\n\n\n

Results<\/h2>\n\n\n\n