File:CONVOLUTIONAL NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF MARITIME VESSELS IN ELECTRO-OPTICAL SATELLITE IMAGERY (IA convolutionalneu1094561255).pdf
Original file (1,275 × 1,650 pixels, file size: 1.68 MB, MIME type: application/pdf, 80 pages)
Captions
Summary[edit]
CONVOLUTIONAL NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF MARITIME VESSELS IN ELECTRO-OPTICAL SATELLITE IMAGERY ( ) | ||
---|---|---|
Author |
Rice, Katherine |
|
Title |
CONVOLUTIONAL NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF MARITIME VESSELS IN ELECTRO-OPTICAL SATELLITE IMAGERY |
|
Publisher |
Monterey, CA; Naval Postgraduate School |
|
Description |
The ability to locate and identify vessels of interest in satellite imagery plays a vital role in maintaining maritime security. Recent studies have demonstrated that convolutional neural networks can be used to automatically classify or detect ships in satellite images; however, this technique requires large amounts of training data and computational power that may not be readily available in an operational environment. We seek to show that the process of transfer learning can be used to adapt open source convolutional neural network architectures pre-trained on large datasets to Department of Defense-specific image classification and detection tasks. We test this hypothesis by retraining both the VGG-16 image classification architecture and a VGG-16 based Single Shot Detector on a dataset comprised of satellite images containing ships. We first examine the performance of these retrained networks on the single category task of classifying or detecting ships in satellite imagery. We then evaluate model performance on datasets in which a fraction of the images contains blur and noise to simulate degraded satellite imagery. Finally, we test the models’ ability to distinguish between subcategories of ships. We show that transfer learning can be leveraged to reduce both the size of the training set and the training time required to produce an effective classification or detection model to meet the Department of Defense’s analysis needs. Subjects: deep learning; machine learning; image classification; object detection; transfer learning; satellite imagery; single shot detector; convolutional neural network |
|
Language | English | |
Publication date | December 2018 | |
Current location |
IA Collections: navalpostgraduateschoollibrary; fedlink |
|
Accession number |
convolutionalneu1094561255 |
|
Source | ||
Permission (Reusing this file) |
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States. |
Licensing[edit]
Public domainPublic domainfalsefalse |
This work is in the public domain in the United States because it is a work prepared by an officer or employee of the United States Government as part of that person’s official duties under the terms of Title 17, Chapter 1, Section 105 of the US Code.
Note: This only applies to original works of the Federal Government and not to the work of any individual U.S. state, territory, commonwealth, county, municipality, or any other subdivision. This template also does not apply to postage stamp designs published by the United States Postal Service since 1978. (See § 313.6(C)(1) of Compendium of U.S. Copyright Office Practices). It also does not apply to certain US coins; see The US Mint Terms of Use.
|
||
This file has been identified as being free of known restrictions under copyright law, including all related and neighboring rights. |
https://creativecommons.org/publicdomain/mark/1.0/PDMCreative Commons Public Domain Mark 1.0falsefalse
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 08:14, 16 July 2020 | 1,275 × 1,650, 80 pages (1.68 MB) | Fæ (talk | contribs) | FEDLINK - United States Federal Collection convolutionalneu1094561255 (User talk:Fæ/IA books#Fork8) (batch 1993-2020 #12362) |
You cannot overwrite this file.
File usage on Commons
The following page uses this file:
Metadata
This file contains additional information such as Exif metadata which may have been added by the digital camera, scanner, or software program used to create or digitize it. If the file has been modified from its original state, some details such as the timestamp may not fully reflect those of the original file. The timestamp is only as accurate as the clock in the camera, and it may be completely wrong.
Short title | CONVOLUTIONAL NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF MARITIME VESSELS IN ELECTRO-OPTICAL SATELLITE IMAGERY |
---|---|
Image title | |
Author | Rice, Katherine |
Software used | Rice, Katherine |
Conversion program | Adobe PDF Library 11.0 |
Encrypted | no |
Page size | 612 x 792 pts (letter) |
Version of PDF format | 1.4 |