A Tool for Vision Based Pedestrian Detection Performance Evaluation

Abstract

This paper describes a system for evaluating pedestrian detection algorithm results. The developed tool allows a human operator to annotate on a file all pedestrians in a previously acquired video sequence. A similar file is produced by the algorithm being tested using the same annotation engine. A matching rule has been established to validate the association between items of the two files. For each frame a statistical analyzer extracts the number of mis-detections, both positive and negative, and correct detections. Using these data, statistics about the algorithm behavior are computed with the aim of tuning parameters and pointing out recognition weaknesses in particular situations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 16, 2004
Accession Number
ADA591088

Entities

People

  • A. Broggi
  • A. Tibaldi
  • M. Bertozzi
  • M. Del Rose
  • P. Grisleri

Organizations

  • University of Parma

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Case Studies
  • Computer Stereo Vision
  • Computer Vision
  • Correlation Analysis
  • Detection
  • Detectors
  • Graphical User Interface
  • Quality Control
  • Radio Transmitters
  • Recognition
  • Sequences
  • Statistics
  • Test And Evaluation
  • Transmitters
  • User Interface

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Science.
  • Computer Vision.