Multi target video tracking using residual vector quantization

  • Salman Aslam
  • , Christopher Barnes
  • , Aaron Bobick

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we use Residual Vector Quantization (RVQ) for multi-target tracking. To the best of our knowledge, this is the first reported application of RVQ to any form of video processing. We implement a completely automatic method of initializing RVQ encoder and decoder codebooks from targets in a crowded scenario, and then use those codebooks to subsequently detect and track targets.

Original languageEnglish
Title of host publicationProceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
Pages642-646
Number of pages5
StatePublished - 2010
Event2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 - Las Vegas, NV, United States
Duration: Jul 12 2010Jul 15 2010

Publication series

NameProceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
Volume2

Conference

Conference2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
Country/TerritoryUnited States
CityLas Vegas, NV
Period07/12/1007/15/10

Keywords

  • σ-tree classifier
  • Compression
  • Machine learning
  • Multi-target tracking
  • Pattern recognition
  • Residual vector quantization
  • Source coding

Fingerprint

Dive into the research topics of 'Multi target video tracking using residual vector quantization'. Together they form a unique fingerprint.

Cite this