Illegal constructions can pose a hazard to the environment and to the occupants of unlawfully constructed buildings. The administrative and financial capacities of municipalities are limited in many small communities, which complicates the early detection of illegal construction activities, as there may not be enough resources to conduct regular compliance inspections. The detection of unpermitted constructions through site visits is time-consuming and inefficient, and this often results in illegal activities being detected in the later stages of the building process.
Solution identifies new construction activity in an area, based on satellite data, filters out unlawful activities based on building permits data and informs users such as local government authorities of activities not covered by permits. We provide this solutions by integrating building registers data with the information about new construction activities. To do so, we utilize machine learning algorithms on satellite data, to recognize constrution activity and combine this data with building register data for our target use case.
There are several companies in the market that offer solutions for infrastructure monitoring based on data from satellites. One aspect, that sets our offering apart from the companies already operating in the market is that our solution foresees integration with building registers, which enables automatic filtering of illegal actives from all detected construction activities.
The following tasks are covered in the activity: 1) validation and improvement of the requirements specification 2) utilization of machine learning algorithms on satellite data, with sufficient precision and recall, to package the analysis software as a web application product; b) combination of satellite data with building register data for our target use case.