Iterated wavelet transformation and signal discrimination for hrr radar target recognition

Abstract

This paper explores the use of wavelets to improve the selection of discriminant features in the target recognition problem using high range resolution (HRR) radar signals in an air to air scenario. We show that there is statistically no difference among four different wavelet families in extracting discriminatory features. Since similar results can be obtained from any of the four wavelet families and wavelets within the families, the simplest wavelet (Haar) should be used. We use the box classifier to select the 128 most salient pseudo range bins and then apply the wavelet transform to this reduced set of bins. We show that by iteratively applying this approach, classifier performance is improved. We call this the iterated wavelet transform. The number of times the feature reduction and transformation can be performed while producing improved classifier performance is small and the transformed features are shown to quickly cause the performance to approach an asymptote.

Intelligent Target Recognition Based on Wavelet Adaptive Network Based Fuzzy Inference System

“…At the same time, the echo signal can be called target range profile. In literature, there are many studies, in which echo signal were used for automatic target recognition [1][2][3][4][5].…”

“…This study will introduce the technique that will aid automatic target recognition, enable further research of target recognition, and provide a novel intelligent system for target recognition [1][2][3]. This study uses a combination of wavelet signal processing and adaptive network based fuzzy inference system to efficiently extract the features from pre-processed real target echo signals for the purpose of automatic target recognition among variety targets.…”

Orthogonal maximum margin projection subspace for radar target HRRP recognition

“…S. K. Wong [11] presents a feature selection method in frequency domain. D. E. Nelson et al [12] study a new iterated wavelet feature for HRRP classification. R. A. Mitchell et al [13] extract some robust statistical features from HRRP for radar target recognition.…”

Non‐cooperative identification of civil aircraft using a generalised mutual subspace method

“…Feature selection methods and dimensionality reduction algorithms are also frequently used in NCTI, including wavelet transformation [14], algorithms based on a reconstruction model such as principal component analysis (PCA) [4], the differential power spectrum [15], linear discriminant functions [16], or singular value decomposition (SVD) [17].…”