Multistatic human micro‐Doppler classification of armed/unarmed personnel

Abstract

Classification of different human activities using multistatic micro-Doppler data and features is considered in this paper, focusing on the distinction between unarmed and potentially armed personnel. A database of real radar data with more than 550 recordings from 7 different human subjects has been collected in a series of experiments in the field with a multistatic radar system. Four key features were extracted from the micro-Doppler signature after Short Time Fourier Transform analysis. The resulting feature vectors were then used as individual, pairs, triplets, and all together before inputting to different types of classifiers based on the discriminant analysis method. The performance of different classifiers and different feature combinations is discussed aiming at identifying the most appropriate features for the unarmed vs armed personnel classification, as well as the benefit of combining multistatic data rather than using monostatic data only. 1-IntroductionThis paper presents the analysis of radar micro-Doppler signatures from a multistatic radar system. The data was generated using NetRAD [1] which is a three-node multistatic radar system that has been developed over the last decade at University College London. The system has been adapted since 2007 to a higher power wireless configuration to increase the flexibility of the measurement possibilities [2], and has provided interesting and novel results in the field of bistatic sea clutter characterisation and analysis [3].Radar Micro-Doppler is the phenomenon of the observed micro-motions on top of the bulk main Doppler component of a target's motion. It has been the subject of research over a number of years focusing on the additional information that can be extracted from this signal.Such information can then be exploited in a variety of applications for security, law enforcement, urban warfare, and search and rescue, where the detection, tracking, and classification of many human targets moving in a cluttered environment is of paramount importance.

Aspect angle dependence and multistatic data fusion for micro‐Doppler classification of armed/unarmed personnel

“…The particular focus was on the discrimination between unarmed and potentially armed personnel. This paper presents significant new elements in comparison with the previous work in [19].…”

“…The classifier used in this work is based on the discriminant analysis method, in particular its diagonal-linear variant which is described in details in [19][20][21]. The assumption of this method is that the samples of each class are represented by a multivariate Gaussian distribution, and the parameters of this distribution (mean and covariance matrix) are estimated during the initial training phase of the classifier.…”

Classification of loaded/unloaded micro‐drones using multistatic radar

“…Following the same approach used to classify human microDoppler signatures, feature samples have been extracted from the spectrograms [7][8] and used as input to a classifier. Two features based on the Doppler and bandwidth centroid of the micro-Doppler signatures have been identified as suitable for the loaded/unloaded classification [9].…”

“…The classifiers used here are the Naïve Bayes and the diagonallinear variant of the discriminant analysis classifier, described in more details in [7,10]. The classifiers are trained with 10% to 30% of the overall samples available, and the remaining data are used to assess the accuracy and calculate the classification error.…”

“…Experimental setup and radar system: The data presented in this paper were collected using the University College London multistatic radar system NetRAD [7]. NetRAD is a coherent pulsed radar consisting of three separate but identical nodes that operates at 2.4 GHz, S-band.…”