Foundations for Summarizing and Learning Latent Structure in Video

Abstract

Video data from a variety of DoD platforms is proliferating in the modern battlespace, and expanded dissemination of this video makes it widely available. However, the detection of artifacts of interest in streaming surveillance video is a manually intensive process. As the volume of video data continues to increase, automated video summarization that highlights artifacts of interest is needed. In this work, we are developing automated and semantically meaningful video summarization and sense making to improve situational awareness, reduce the amount of manual processing necessary, and increase the volume of video data that can be analyzed in near real-time.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2017
Accession Number
AD1088350

Entities

People

  • Kevin Pitstick

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Automated Text Summarization
  • Copyrights
  • Department Of Defense
  • Engineering
  • Full Motion Video
  • Governments
  • Guarantees
  • Learning
  • Machine Learning
  • Materials
  • Pipelines
  • Robotics
  • Software Development
  • Surveillance
  • Training
  • Universities
  • Video

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development