Radar target recognition using range profiles

Zyweck, A.; Bogner, R.E.

doi:10.1109/icassp.1994.389643

Cited by 9 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The HRRP is typically used to derive features that form the basis for a reference library against which features derived from an unknown target are compared [5][6][7]. The HRRP is first subjected to a threshold from which feature sets are derived.…”

Section: Introductionmentioning

confidence: 99%

On variability in high resolution range profiles

Doo

Smith

Baker

2013

2013 International Conference on Radar

View full text Add to dashboard Cite

Radar target classification often uses feature sets derived from high range resolution profiles as an input to a classifier. However, rage profiles typically exhibit variability that is subsequently passed on to the feature vectors used in classification. This results in degraded classification performance as the variance in the feature vectors is too large and the mean distance between feature vector too small. In this paper we examine the fundamental causes of such variability. Specifically we demonstrate via modeling, simulation and experimentation that (i) the output of the matched filter is a sensitive function of the relative position of scatters distributed along the length of a target and (ii) the apparent location of a scatterers phase center is a sensitive function of viewing angle causing significant variability even over orientation changes of a fraction of a degree.

show abstract

Section: Introductionmentioning

confidence: 99%

On variability in high resolution range profiles

Doo

Smith

Baker

2013

2013 International Conference on Radar

View full text Add to dashboard Cite

show abstract

“…In this paper we concentrate on the particular situation in which a single non-cooperative target has been previously detected and tracked by the system. The improvement in performance due to the available multiplicity of perspectives is investigated examining onedimensional signatures and the classification is performed on raw data with noise floor offset removed by target normalization [8]. After generating a target mask in the range profile, the noise level is measured in the non-target zone and then subtracted from the same area.…”

Section: Radar Target Classificationmentioning

confidence: 99%

Multi-perspective target classification

Vespe

Baker

Griffiths

IEEE International Radar Conference, 2005.

View full text Add to dashboard Cite

Traditional radar classification is based on a single aspect view of the target. It is remarkably sensitive to the particular direction under which the target is sensed. A network of radars offers means of collecting backscattered radiation of a range of viewing angles. This offers multi-perspective data sets as an aid to improve radar target classification. By definition, this will provide a data set with higher information content. In this paper we examine whether this approach is useful for classification purposes. Results using full scale turntable demonstrate significant improvements in performance over and above the monostatic case.0-7803-8882

show abstract

“…More over. the dimension of the feature vector given such way is nr that is much smaller than that of the range profile used as a good feature vector as mentioned by many other papers [5] [GI. So we can expect much less computation burden to the following classifier.…”

Section: Feature Representation and Performance Analysismentioning

confidence: 99%