Machine learning is being utilized in more and more projects. It is the science of getting computers to act without being explicitly programmed. Over the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. This interesting news came from Commercial UAV News in their article, “Pix4D Extends Drone-based Imagery with Machine Learning Techniques.”

Most recently, machine learning technology is being used for image classification of drone-based point clouds – a set of data points in the coordinate system. Pix4D software is mostly known for photogrammetry from drone-captured imagery, but its latest mapping innovations is a feature that automatically classifies drone-based point clouds, based on machine learning techniques. By using this feature, entire 3D point clouds are classified into individual groupings, divided into categories such as buildings, roads or vegetation.

The next step of this project will include further development of the classification scheme so that buildings can be extracted and modeled as a semantic composition of geometry, providing more details and refinement.

Melody K. Smith

Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.