Machine Learning (ML) and AI used to identify objects, features from geospatial imagery
ProDroneWorx and its partners are using machine learning and artificial intelligence to identity objects, features, structural information etc from geo-spatial imagery. We use a combination of technologies to solve critical data problems for our clients over cities or rural areas e.g. counting objects for traffic flow or parking in a particular area, generating detailed land use cover maps, etc.
We’re using state of the art machine learning models based on neural networks and computer vision algorithms. The algorithms are trained on different use cases from large datasets. The system can detect individually specified items from the geo-spatial data. For each detection of an item, the proprietary models are applied to ensure the detected object is actually what’s required. The pattern recognition also suppresses false positives. The algorithms detect individual specified items with all physical aspects like their position, object class, size and colours captured.
We can cover large geo-spatial areas using manned aircraft or drones while decreasing contract time and providing our clients with accurate data which enables them to make better informed decisions for their projects.