Picterra has announced the launch of its online custom detector software, allowing users to build their own artificial intelligence model to detect objects in aerial and satellite images. The software tool is ideal for post-processing of surveying and mapping data gathered by unmanned aerial vehicles (UAVs).
Without any previous machine learning experience, the new tool allows users to create their own AI detection model and train it to identify their specific objects of interest in a few steps. The custom model then detects the type of objects defined by the user. It is possible to export these detections and incorporate them into any geospatial analytics workflow as a .csv file or in a variety of georeferenced formats (KML, GeoJSON, and Shapefile) for mapping applications. The tool has a broad variety of possible uses, including detecting buildings, precision agriculture, stock taking, identifying solar panels, and many more types of objects and applications defined by the users of the platform themselves.
“So far I am beyond impressed by the quality of the results we are obtaining from this service. Within a day, I was able to upload my imagery and run the analysis on about 25% of them. The data being output by the program is matching up with what I was expecting and I am already nearing the point of being ready to calculate statistics. It is a huge time saver,” said Andrew E. Ortega, Pilot & Data Processing Specialist, UF Unmanned Aircraft Systems Research Program.