Surface Ship Classification Using Multipolarization, Multifrequency Sky-Wave Resonance Radar
Abstract
Experiments investigating the classification of surface ships using processed radar returns are described. The calibrated and scaled backscatter measurements of scale-model ships at several aspect and elevation angles are used to establish a catalog representing the HF sky-wave resonance region radar returns of actual ship targets. The performance of both the nearest neighbour algorithm, (using frequency domain data), and a correlation algorithm (using time domain data), is investigated. The effects of wave polarization, aspect angle, elevation angle and other key parameters are examined. The consequences of introducing forced errors into the estimates of aspect and elevation angle are studied. A novel feature set employing the ratio of vertically and horizontally polarized radar returns is described, and its classification performance is examined. In general, classification is found to be very much dependent on the particular aspect angle and polarization of interest. The time domain algorithm, vertical polarization, and bow and stern aspects are the parameters which yield best all-round classification performance. Increasing the number of classification frequencies improves performance, but only to a limit. Errors in aspect angle and especially in elevation angle are found to significantly degrade classification performance. A number of suggestions for improving the classification process are discussed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1984
- Accession Number
- ADA163027
Entities
People
- Neil F. Chamberlain
Organizations
- Ohio State University