Accession Number:

AD1104208

Title:

Semantic Segmentation for Aerial Imagery Using U-Nets

Descriptive Note:

Technical Report,01 Sep 2018,01 Mar 2020

Corporate Author:

AIR FORCE INSTITUTE OF TECHNOLOGY WRIGHT-PATTERSON AFB OH WRIGHT-PATTERSON AFB United States

Personal Author(s):

Report Date:

2020-03-19

Pagination or Media Count:

98.0

Abstract:

In situations where global positioning systems are unavailable, alternative methods of localization must be implemented. A potential step to achieving this is semantic segmentation, or the ability for a model to output class labels by pixel. This research aims to utilize datasets of varying spatial resolutions and locations to train a fully convolutional neural network architecture called the U-Net to perform segmentations of aerial images. Variations of the U-Net architecture are implemented and compared to other existing models in order to determine the best in detecting buildings and roads. A final dataset will also be created combining two datasets to determine the ability of the U-Net to segment classes regardless of location. The final segmentation results will demonstrate the overall efficacy of semantic segmentation for different datasets for potential localization applications.

Subject Categories:

  • Navigation and Guidance

Distribution Statement:

APPROVED FOR PUBLIC RELEASE