Through Wall Radar Classification of Human Micro-Doppler using Singular Value Decomposition Analysis

Abstract

Abstract:The ability to detect the presence as well as classify the activities of individuals behind visually obscuring structures is of significant benefit to police, security and emergency services in many situations. This paper presents the analysis from a series of experimental results generated using a through-the-wall (TTW) Frequency Modulated Continuous Wave (FMCW) C-Band radar system named Soprano. The objective of this analysis was to classify whether an individual was carrying an item in both hands or not using micro-Doppler information from a FMCW sensor. The radar was deployed at a standoff distance, of approximately 0.5 m, outside a residential building and used to detect multiple people walking within a room. Through the application of digital filtering, it was shown that significant suppression of the primary wall reflection is possible, significantly enhancing the target signal to clutter ratio. Singular Value Decomposition (SVD) signal processing techniques were then applied to the micro-Doppler signatures from different individuals. Features from the SVD information have been used to classify whether the person was carrying an item or walking free handed. Excellent performance of the classifier was achieved in this challenging scenario with accuracies up to 94%, suggesting that future through wall radar sensors may have the ability to reliably recognize many different types of activities in TTW scenarios using these techniques.

Through the Wall, Recognize Moving Targets Based on Micro-Doppler Signatures

“…Where, Lui et al [19] studied the motion detection and recognition based on MD through the homogeneous non-magnetic walls, where they show that the signatures are unaltered as corroborated by Ram et al In [20]. In this context, Chen et al in [10], [21] presented a recognition study through two different 10 cm -thick walls, concrete blocks and plastic, for medical application. In [6] was concentrated to the through the walls classification accuracy by using the support vector machine for S-band at long range.…”

“…In through-the-wall radar design and its return signal analysis, the properties of that wall represent critical factors which affected on the attenuation, dispersion, reflection, and refraction of the return signal and then on the Doppler signatures [23], [10]. The effect of the walls on the, Tx/Rx below X band, radar signals are concentrated in two points; the first one is the effect on the signal phase, this effect is simple and constant because of the wall is stationary.…”

On the Application of Digital Moving Target Indication Techniques to Short-Range FMCW Radar Data

“…Background subtraction is based on an estimation of the background clutter in a measurement scene over some period of measurement time, which is then subtracted from future measurements for some period of time before the estimation is updated. This is also sometimes described as coherent change detection [2], [3], and has been used to improve the performance of classification processes [14], [15]. The process is described as follows:…”

DopNet: A Deep Convolutional Neural Network to Recognize Armed and Unarmed Human Targets

“…As for the selection of classifiers, various research work related to classifiers in machine learning community have been proposed [5,12,13,22]. However, these features and classifiers have not been developed and optimized in the same joint framework.…”