MIST: An Interactive Machine Learning Application for Video Segmentation

reportActive / Technical Report | Accesssion Number: AD1123739 | Open PDF

Abstract:

This document presents the background, implementation details, and preliminary results for the U.S. Naval Research Laboratory's proprietary Motion Imagery Segmentation Tool (MIST), an application built for Matlab. This report is self-contained in explaining the necessary concepts within the fields of statistics, machine learning, and computer vision in order to understand the inner workings of the MIST application and the preliminary results.

Author(s):
Smith, Laura K ; Michael, Chris J
Author Organization(s):
Naval Research Laboratory
Funding Organization(s):
Publication Date:
2021 Feb 25
Pagination:
0

Security Markings

RECORD

Collection: TRECMS
Subject Terms
Modernization Areas:
Autonomy
Communities of Interest:
No COI(s) Identified
Descriptor(s):
information science, neural networks, artificial intelligence software, machine learning, supervised machine learning, artificial intelligence, computer languages, computer vision, computers, graphical user interface, pattern recognition, image segmentation, data sets, deep learning, image recognition, dimensionality reduction, geographic regions
Subject Categories:
Mathematical and Computer Sciences
Update Date:
2021 Mar 01