Detection and tracking of multiple metallic objects in millimetre-wave images

C. D. Haworth, Y. De Saint-Pern, D. Clark, E. Trucco, Y. R. Petillot

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

In this paper we present a system for the automatic detection and tracking of metallic objects concealed on moving people in sequences of millimetre-wave (MMW) images. The millimetre-wave sensor employed has been demonstrated for use in covert detection because of its ability to see through clothing, plastics and fabrics. The system employs two distinct stages: detection and tracking. In this paper a single detector, for metallic objects, is presented which utilises a statistical model also developed in this paper. The second stage tracks the target locations of the objects using a Probability Hypothesis Density filter. The advantage of this filter is that it has the ability to track a variable number of targets, estimating both the number of targets and their locations. This avoids the need for data association techniques as the identities of the individual targets are not required. Results are presented for both simulations and real millimetre-wave image test sequences demonstrating the benefits of our system for the automatic detection and tracking of metallic objects. © 2006 Springer Science + Business Media, LLC.

Original languageEnglish
Pages (from-to)183-196
Number of pages14
JournalInternational Journal of Computer Vision
Volume71
Issue number2
DOIs
Publication statusPublished - Feb 2007

Keywords

  • Detection
  • Metallic objects
  • Millimetre-wave
  • Tracking

Fingerprint Dive into the research topics of 'Detection and tracking of multiple metallic objects in millimetre-wave images'. Together they form a unique fingerprint.

  • Cite this