Video Analytics Evaluation: Survey of Datasets, Performance Metrics and Approaches

Abstract

This report presents a survey of evaluation datasets, metrics and practices used by the scientific community pertaining to the evaluation of video analytics in the video surveillance context. The focus of the survey is on the task of visually tracking people in video, and its application to loitering and tailgating detection. The related key results from the TRECVID video analytic evaluation conducted by the National Institute of Standards and Technology (NIST) are presented.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2014
Accession Number
AD1018025

Entities

People

  • Diego Macrini
  • Dmitry O. Gorodnichy
  • Robert Laganiere

Organizations

  • Canada Border Services Agency

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Computer Graphics
  • Computer Science
  • Computer Vision
  • Computers
  • Data Mining
  • Data Sets
  • Databases
  • Detection
  • Electrical Engineering
  • Event Detection
  • Human Behavior
  • Information Science
  • Machine Learning
  • Multiple Hypothesis Tracking
  • National Security
  • Network Science
  • Person Tracking

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Military Science and Technology Research and Modernization.
  • Organizational Process Management (OPM).