search menu icon-carat-right cmu-wordmark

A Brief Introduction to the Evaluation of Learned Models for Aerial Object Detection

May 2022 White Paper
Eric Heim

The SEI AI Division assembled guidance on the design, production, and evaluation of machine-learning models for aerial object detection.


Software Engineering Institute


Aerial object detection provides critical information for many domains. Machine learning (ML) automatically processes the huge amount of data from aerial imagery and helps human analysts extract actionable information. Determining which aerial object detectors yield accurate results is important for organizations seeking to develop, acquire, or deploy this technology. This document provides part of the necessary practical guidance to develop and evaluate ML models for aerial object detection.