Performance Evaluation of Neuromorphic-Vision Object Recognition Algorithms

Abstract

The U.S. Defense Advanced Research Projects Agency's (DARPA) Neo vision2 program aims to develop artificial vision systems based on the design principles employed by mammalian vision systems. Three such algorithms are briefly described in this paper. These neuromorphic - vision systems' performance in detecting objects in video was measured using a se t of annotated clips. This paper describes the results of these evaluations including the data domains, metrics , methodologies, performance over a range of operating points and a comparison with computer vision based baseline algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2014
Accession Number
ADA618770

Entities

People

  • Dmitry Goldgol
  • Douglas D. Hackett
  • Eric Krotkov
  • Gill Pratt
  • Mark Anderson
  • Qinfen Zheng
  • Rajeev Sharma
  • Rajmadhan Ekambaram
  • Rangachar Kasturi
  • Yang Rang

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Computers
  • Detection
  • Information Science
  • Neural Pathways
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Statistical Analysis
  • Target Recognition
  • Test And Evaluation
  • Test Sets
  • Video Clips

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Distributed Systems and Data Platform Development
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy