Using Evidence Feed-Forward Hidden Markov Models

Abstract

Visual Understanding is an increasing field of research thanks to the advances in image processing, object detection, classification, and advanced computational intelligence techniques. Hidden Markov Models (HMM) are one of these techniques which have been used extensively for this problem. This paper will introduce a new type of HMM, called Evidence Feed Forward Hidden Markov Models, that not only increase the classification rate for sparse messy data, but outlines a whole new theory towards changing the way HMM's are conceived. Data is taken from simulated images of people's actions. Over processing is performed to decrease the likelihood of correct classification. Finally, the over processed, sparse data is used to train and test the Evidence Feed-Forward HMM and the standard HMM. Results are compared.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 11, 2010
Accession Number
ADA543331

Entities

People

  • Christian Wagner
  • Michael S. Del Rose
  • Philip Frederick

Organizations

  • United States Army Tank Automotive Research, Development and Engineering Center

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Classification
  • Detection
  • Hidden Markov Models
  • Human Behavior
  • Identification
  • Identification Systems
  • Machine Learning
  • Markov Models
  • Models
  • Observation
  • Probability
  • Recognition
  • Security
  • Standards

Fields of Study

  • Engineering

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design