Recognition of In-Vehicle Group Activities (iVGA): Phase-I, Feasibility Study

Abstract

The objective of this proposed research effort is to conduct a feasibility study of in-vehicle Group Activities (iVGA) and develop suitable context-based taxonomy and ontology schemas for coherent analysis and inferencing of such activities. The prime objective of feasibility study is to identify suitable automated computer vision-based techniques enabling low false alarm rate identification of iVGA. Another objective is to develop a suitable virtual simulation environment as a test bed for staging appropriate context-based scenarios exhibiting different iVGA for testing and evaluation of newly developed ontology, algorithms and techniques. The goal is map visual observations of iVGA to annotated messages describing spatiotemporal behaviors exhibited in the confined space of a vehicle in lieu of physical obstructions and inevitable occlusions. In this project, partially observable spatiotemporal imagery data are analyzed to reason, predict, and discriminate group activities occurring in confined spaces.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 27, 2014
Accession Number
ADA622951

Entities

People

  • Amir Shirkhodaie

Organizations

  • Tennessee State University

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Computational Science
  • Computer Graphics
  • Computer Vision
  • Detection
  • Detectors
  • Human-Machine Interaction
  • Image Processing
  • Information Processing
  • Machine Learning
  • Mathematics
  • Neural Networks
  • Ontologies
  • Recognition
  • Students
  • Technology Transfer

Readers

  • Computer Vision.
  • Software Engineering
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Space
  • Space - Space Objects