Real-Time Multi-Resolution Blob Tracking

Abstract

This paper introduces a new real-time blob tracking algorithm. Segmentation is the first step in many video analysis approaches. A number of successful segmentation techniques extract regions of interest, or blobs, in successive frames. the problem addressed here is that of establishing temporal relationships between blobs, without the use of domain-specific information. These relationships can then be analyzed at a higher semantic level. The proposed algorithm maintains a multi-resolution tracking graph that encodes, at each resolution, the temporal relationships of the blob detected in successive frames. As hypotheses generation, propagation and refinement approach allows to track not only large, slow blobs but also small, fast blobs. Tracking performance is illustrated on various simple application scenarios using a real-time implementation of an integrated segmentation and tracking systems. Blob tracking results are demonstrated on standard video surveillance datasets, as well as real-time ball (and player) tracking results in professional tennis and racquetball videos.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 2004
Accession Number
ADA447622

Entities

People

  • Alexandre R. Francois

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • California
  • Computations
  • Computer Vision
  • Hypotheses
  • Images
  • Intelligent Systems
  • Kalman Filters
  • Materials
  • Parallel Computing
  • Parallel Processing
  • Sequences
  • Trajectories
  • Two Dimensional
  • Video
  • Video Surveillance

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Distributed Systems and Data Platform Development