Target detection of ISAR data by principal component transform on co-occurrence matrix
Highlights
► We postulate ISAR data may not require Fourier transform for visualization. ► PCT provides a good alternative for processing ISAR signal data matrix. ► Additional GLCM processing enhances automated target detection without creating specific thresholding cut offs. ► This work has been done on simulated ISAR data needs confirmation by actual experimentation.
Introduction
Target detection is essential for target interpretation and analysis in Inverse Synthetic Aperture Radar (ISAR) imaging system. In ISAR, the target rotates and the radar is stationary and the target images can be obtained by transmitting wideband signals, and high cross range resolution is obtained by coherently accumulating number of echoes from different aspect angles. The goal of ISAR imaging system is to detect the targets particularly for surveillance. The conventional target detection system for ISAR images consists of the following stages: fast time filtering, slow time filtering, compression and decompression for focused FFT and IFFT response, Anti-aliasing and Matched Filtering. This paper proposed an algorithm for target detection for ISAR images which is based on co-occurrence matrix. Co-occurrence matrix is the statistical approach for texture representation and first introduced by Haralick et al. using the grey level co-occurrence matrix (GLCM) (Haralick et al., 1973). Co-occurrence matrix has been used to extract structural similarities between the objects (Mita et al., 2008, Jing Yi Tou et al., 2009), for classification (ZHU Le-Qing, 2010) and for segmentation (Corneloup, 1996). Co-occurrence matrix method also used by Clausi and Jerniganl (1998), where they proposed an improvement on the GLCM by presenting a grey level co-occurrence linked list (GLCLL) structure that stores the non-zero co-occurring probabilities in a sorted linked list. Rignot and Kwok (1990) have analyzed SAR images using texture features computed from gray level co-occurrence matrices. Threshold has been determined by using entropies, global, local and joint from co-occurrence matrix (Park et al., 2011, Mark et al., 1995, Chang et al., 1994).
A co-occurrence matrix captures the spatial dependence of contrast values, depending on different directions and distances specified. For a given matrix A with spatial dimension m × n with L gray levels G = 1, 2, 3, …, L. The gray levels of co ordinate (x, y) is denoted by , the co-occurrence C of A is an L × L matrixwhich contains the transition of gray levels with its adjacent gray levels. For the gray levels (i, j) the (i, j)th entry of the co-occurrence matrix C, is defined as if otherwise
The probability of the occurrence is defined as
As such, the co-occurrence matrix can better expose the underlying nature of texture than can a Fourier description. This is because the co-occurrence measures spatial relationships between brightness, as opposed to frequency content. This clearly gives alternative results.
Many feature vectors has been computed from GLCM (Haralick et al., 1973, Tuceryan and Jain, 1998). Falconer et al. (2006) measured the power spectral density (PSD) of a variety of objects and used the differences in the shaping of the PSD (kurtosis and energy band) to differentiate between targets and infer the activity level (i.e., resting versus moving) of human targets. Sabatini and Colla (1998) used wavelet transforms to remove the high-frequency components and reconstruct the signal; the error between the original and reconstructed signals was then used to compute a threshold for discriminating between targets. López-Estrada and Cumplido (2009) used co occurrence matrix to evaluate the cluttered environment in a given image.
In detection module, firstly the raw data are processed for target detection by using co-occurrence matrix of the gray scale image. Principal component transform (PCT) using covariance has been done by taking co-occurrence matrix as input. Furthermore,it has been noticed that after applying the proposed method number of targets presents in the environment are clearly identified.
The paper is organized as follows; In Section 2 Methodology for capturing and preprocessing of ISAR data and algorithm for target detection has been given. Section 3 represents with all the results and discussion. Finally, conclusions are included in Section 4.
Section snippets
Methodology
In ISAR the target motion provides the changes in relative velocity that cause different Doppler shifts to occur across the target Skolnik, 2001. The images in ISAR are generally obtained by the range-Doppler algorithm based on the 2-D Fourier transform (Fig. 1). The received RADAR signals from targets are always superposed with the receiver noise and other disturbing signals. These disturbing signals are always randomly fluctuating due to the nature of their origin. RADAR targets are very
Result and discussion
The received matrix size for the experimental data is 21 × 181.Two targets were placed in the cluttered environment. The pre-processing steps for data capturing has already been discussed in Section 2.1.The whole environment for this experiment is in a real time environment so rejection of clutter is difficult. Fig. 4(a) shows the image of the captured RADAR data after preprocessing by conventional approach. Fig. 4(c) depicts an image for probability of co-occurrence matrix which shows that there
Conclusion
The proposed method is innovative as this a method which detects targets from cluttered environment which is not threshold dependent. By dimensionality reduction the proposed method proves its computational efficiency. Co-occurrence matrix shows the sub patterns those formed by intensity pairs and the frequency with which they occur. A transformation on co occurrence matrix has been done which extracts the principal feature components which are not dependent on any threshold selection point.
References (15)
A relative entropy based approach to image thresholding
Pattern Recognit. Soc.
(1994)Bscan image segmentation by thresholding using cooccurrence matrix analysis
Pattern Recognition
(1996)- et al.
A method for sonar based recognition of walking people
Robot. Autonom. Syst.
(1998) - et al.
A fast method to determine cooccurrence texture features
IEEE Trans. Geosci. Remote Sensing
(1998) - Falconer D.G. et al., 2006. Robot-mounted through-wall radar for detecting locating and identifying building occupants....
Texture features for image classification
IEEE Trans. Systems Man Cybernet.
(1973)- Jing Yi Tou et al., 2009. Rotational invariant wood species recognition through wood species verification, In: First...