Accession Number:

AD1076436

Title:

Unresolved Object Detection Using Synthetic Data Generation and Artificial Neural Networks

Personal Author(s):

Corporate Author:

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

Report Date:

2019-03-01

Abstract:

This research presents and solves constrained real-world problems of using synthetic data to train artificial neural networks ANNs to detect unresolved moving objects in wide field of view WFOV electro-opticalinfrared EOIR satellite motion imagery. Objectives include demonstrating the use of the Air Force Institute of Technology AFIT Sensor and Scene Emulation Tool ASSET as an effective tool for generating EOIR motion imagery representative of real WFOV sensors and describing the ANN architectures, training, and testing results obtained. Deep learning using a 3-D convolutional neural network 3D ConvNet, long short term memory LSTM network, and U-Net are used to solve the problem of EOIR unresolved object detection. U-Net is shown to be a promising ANN architecture for performing EOIR unresolved object detection. In two of the experiments, U-Net achieved 90 percent and 88 percent pixel prediction accuracy. In addition, the results show ASSET is capable of generating sufficient information needed to train deep learning models.

Descriptive Note:

Technical Report

Pages:

0077

Descriptors:

Identifiers:

Subject Categories:

Communities Of Interest:

Modernization Areas:

Distribution Statement:

Approved For Public Release;

File Size:

12.62MB

View The Document