Track-to-Track Association in Ocean Surveillance
Abstract
The ability to resolve track-to-track association problems is one of the most important requirements in the development of automated information processors for ocean surveillance systems comprising multiple data sources. The individual tracks carried by a processor can be represented as samples from multivariate normal distributions, and the most basic track association problem- determining whether two tracks relate to the same target-is solved using a test based on the chi-square distribution. When a specified track is to be compared with two other candidates for association, a test of the chi-square distribution against a noncentral chi-square alternative is used; this procedure can be adapted for use as a sequential test in continuing surveillance operations. The procedures developed for track association can be implemented within man-machine systems; for many cases they will make relatively few demands for interaction by surveillance analysts. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- May 12, 1976
- Accession Number
- ADB011564
Entities
People
- Howard L. Wiener
Organizations
- United States Naval Research Laboratory