Student Work

Feature Recognition from Aerial Images Using Machine Learning

公开 Deposited

可下载的内容

open in viewer

The military utilizes parafoil parachutes to deliver supplies to soldiers in the field using GPS. Some issues arise when using GPS. As these deliveries contain important supplies, it is critical that methods are developed to prevent these interferences. We developed a more intuitive user interface for a simulator designed last year, as well as a second simulator that allows users to simulate a horizontal flight, rather than a vertical drop. Lastly, we created two machine learning models. The first was a transfer learning model which was able to take high altitude images and segment them based on geographic regions. The second was a Neural Network that could take in the labeled images from the transfer learning model in pairs and predict how much position has changed between the two photos.

  • This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
Creator
Publisher
Identifier
  • 95216
  • E-project-032423-140416
关键词
Advisor
Year
  • 2023
Sponsor
Date created
  • 2023-03-24
Resource type
Major
Source
  • E-project-032423-140416
Rights statement
最新修改
  • 2023-04-12

关系

属于 Collection:

项目

单件

Permanent link to this page: https://digital.wpi.edu/show/hx11xj644