Recognition of humans based on radar micro‐Doppler shape spectrum features

Ricci, R.; Balleri, Alessio

doi:10.1049/iet-rsn.2014.0551

Cited by 66 publications

(50 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another noticeable trend is the fact that the classification accuracy increases with increasing spectrogram window when the overlap is high (95% to 50% for the discriminant analysis classifier and 95% to 75% for Naïve Bayes classifier), but the accuracy decreases with increasing spectrogram length when low overlap is used. These results appear to be in line with those in [9], where the authors report that they required overlap of at least over 40% to achieve good classification The best result overall appears to be the use of 0.7 s window with 95% overlap and binary voting approach, but only a slight reduction of performance of less than 2% is reported when using lower overlap at around 75% and 50%. An example of unarmed vs armed spectrograms calculated with 0.7 s window and 50%…”

Section: Single Target Datasupporting

confidence: 86%

“…The recorded data were processed through STFT to characterize the micro-Doppler signature in the armed vs unarmed case through features that can be extracted from the spectrograms, as in [6][7][8][9]. The STFTs were initially calculated using 0.…”

Section: Discussionmentioning

confidence: 99%

“…Target identification and classification based on micro-Doppler signatures have been investigated over a number of years for a variety of applications in security, warfare, search and rescue context [3,4]. It has been shown how human microDoppler signatures collected using a monostatic radar system and analysed through Short Time Fourier Transform (STFT) can be used to discriminate between animals and humans [5,6] , to distinguish between different activities performed by different people such as running, walking, crawling [7,8] or to identify different people performing the same activity on the basis of different micro-motion patterns [9] , and even to potentially distinguish between men and women [10] .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Fioranelli

Ritchie

Griffiths

2016

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

Fioranelli, F., Ritchie, M., and Griffiths, H. (2016) Centroid features for classification of armed/unarmed multiple personnel using multistatic human microdoppler. IET Radar, Sonar and Navigation, (doi:10.1049/iet-rsn.2015.0493) This paper is a postprint of a paper submitted to and accepted for publication in IET Radar, Sonar and Navigation and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library There may be differences between this version and the published version. You are advised to consult the publisher's version if you wish to cite from it.http://eprints.gla.ac.uk/118776/ AbstractThis paper analyses the use of human micro-Doppler signatures collected using a multistatic radar system to identify and classify unarmed and potentially armed personnel walking within a surveillance area. The signatures were recorded in a series of experimental tests and analysed through Short Time FourierTransform followed by feature extraction and classification. Features based on Singular ValueDecomposition and on the centroid of the micro-Doppler signature are proposed and their suitability for armed vs unarmed classification purposes discussed. It is shown that classification accuracy above 95%can be achieved using a single feature. Features based on the centroid of the signatures are shown to be also effective in cases where there are two people walking together in the same direction and at similar speed, and one of them may be armed or not, i.e. for targets not easily separable in range or in Doppler.

show abstract

Section: Single Target Datasupporting

confidence: 86%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Fioranelli

Ritchie

Griffiths

2016

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

show abstract

“…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].…”

Section: Fig 2 Micro-doppler Signatures For the Drone Hovering: (A) mentioning

confidence: 99%

Classification of loaded/unloaded micro‐drones using multistatic radar

et al. 2015

View full text Add to dashboard Cite

This letter presents preliminary results on the use of multistatic radar and micro-Doppler analysis to detect and discriminate between microdrones hovering carrying different payloads. Two suitable features related to the centroid of the micro-Doppler signature have been identified and used to perform classification, investigating also the added benefit of using information from a multistatic radar as opposed to a conventional monostatic system. Very good performance with accuracy above 90% has been demonstrated for the classification of hovering micro-drones.

show abstract

“…It has been shown how features extracted from the Short Time Fourier Transform (STFT) of these signatures can be used to classify human targets from animals and vehicles in a ground surveillance radar context [6,7], to discriminate between different activities performed by people such as walking, running, crawling [8][9][10][11][12][13], and even to identify specific individuals performing the same activity by exploiting the characteristic walking gait and small movement patterns that each individual exhibits [14][15][16]. Time-frequency transforms [4] other than STFTs have been also proposed to characterise micro-Doppler signatures, such as the Gabor transform, Wigner-Ville transform, Cohen's class timefrequency distributions [17] or Empirical Mode Decomposition [18,19], all of which have been shown to be effective in representing minute movements [18].…”

Section: Introductionmentioning

confidence: 99%

Feature Diversity for Optimized Human Micro-Doppler Classification Using Multistatic Radar

Fioranelli

Ritchie

Gürbüz

et al. 2017

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

Feature diversity for optimized human micro-doppler classification using multistatic radar. IEEE Transactions on Aerospace and Electronic Systems, 53(2), pp. 640-654. (doi:10.1109/TAES.2017.2651678) This is the author's final accepted version.There may be differences between this version and the published version. FEATURE DIVERSITY FOR OPTIMIZED HUMAN MICRO-DOPPLER CLASSIFICATION USING MULTISTATIC RADARFrancesco Fioranelli (1) , Matthew Ritchie (2) , Sevgi Zübeyde Gürbüz (3) , Hugh Griffiths (2) ( AbstractThis paper investigates the selection of different combinations of features at different multistatic radar nodes, depending on scenario parameters, such as aspect angle to the target and signal-to-noise ratio, and radar parameters, such as dwell time, polarisation, and frequency band. Two sets of experimental data collected with the multistatic radar system NetRAD are analysed for two separate problems, namely the classification of unarmed vs potentially armed multiple personnel, and the personnel recognition of individuals based on walking gait. The results show that the overall classification accuracy can be significantly improved by taking into account feature diversity at each radar node depending on the environmental parameters and target behaviour, in comparison with the conventional approach of selecting the same features for all nodes.

show abstract

Recognition of humans based on radar micro‐Doppler shape spectrum features

Cited by 66 publications

References 33 publications

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Classification of loaded/unloaded micro‐drones using multistatic radar

Feature Diversity for Optimized Human Micro-Doppler Classification Using Multistatic Radar

Contact Info

Product

Resources

About