DETECTION OF SMALL MOVING OBJECTS IN IMAGE SEQUENCES USING MULTISTAGE HYPOTHESIS TESTING.

Steven D. Blostein, Thomas S. Huang

Research output: Contribution to journalConference articlepeer-review

Abstract

The detection of small, low-contrast, moving objects in a time sequence of digital images is addressed. Since object positions and velocities are unknown, a large number of candidate trajectories, organized into a treestructure, are hypothesized at each pixel. At each root image-pixel, trajectory extensions are mapped to tree nodes. Pixels along a trajectory are tested sequentially for a shift in mean intensity using multistage hypothesis testing (MHT). The MHT is designed according to prespecified error probabilities. Exact, closed-form expressions for MHT test performance are derived and then applied to predict the algorithm's computation and memory requirements. Under a Gaussian white noise background assumption, it is shown theoretically that over 4000 candidate trajectories per pixel are tested using an average of only 30 additions and threshold comparisons.

Original languageEnglish (US)
Pages (from-to)1068-1071
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - Jan 1 1988

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'DETECTION OF SMALL MOVING OBJECTS IN IMAGE SEQUENCES USING MULTISTAGE HYPOTHESIS TESTING.'. Together they form a unique fingerprint.

Cite this