Skip to main content Accessibility help

Self-similarity matrix based slow-time feature extraction for human target in high-resolution radar

  • Yuan He (a1), Pascal Aubry (a1), Francois Le Chevalier (a1) and Alexander Yarovoy (a1)


A new approach is proposed to extract the slow-time feature of human motion in high-resolution radars. The approach is based on the self-similarity matrix (SSM) of the radar signals. The Mutual Information is used as a measure of similarity. The SSMs of different radar signals (high-resolution range profile, micro-Doppler, and range-Doppler video sequence) are compared, and the angel-invariant property of the SSMs is demonstrated. The SSM for different activities (i.e. walking and running) is extracted from range-Doppler video sequence and analyzed. Finally, simulation result is validated by experimental data.


Corresponding author

Corresponding author: Y. He Email:


Hide All
[1]Ram, S.S.; Christianson, C.; Youngwook, K.; Ling, H.: Simulation and analysis of human Micro-Dopplers in Through-Wall environments. IEEE Transact. Geosci. Remote Sens., 48 (2010), 20152023.
[2]Vignaud, L.; Ghaleb, A.; Le Kernec, J.; Nicolas, J.M.: Radar high resolution range and micro-Doppler analysis of human motions, in International Radar Conf., France, 2009.
[3]Fogle, O.R.; Rigling, B.D.: Micro-range/micro-Doppler feature extraction and association, in IEEE Radar Conf., USA, 2011.
[4]Chen, V.C.: Analysis of radar micro-Doppler with time-frequency transform, in Tenth IEEE Workshop on Statistical Signal and Array Processing, USA, 2000.
[5]Chen, V.C.: The Micro-Doppler Effect in Radar, Artech House, Norwood, MA, USA, 2011.
[6]Cutler, R.; Davis, L.: View-based detection and analysis of periodic motion, in Fourteenth Int. Conf. Pattern Recognition, Australia, 1998.
[7]BenAbdelkader, C.; Cutler, R.; Davis, L.: Gait recognition using image self-similarity. EURASIP J. Appl. Signal Process., 4 (2004) 572585.
[8]Junejo, I.N.; Dexter, E.; Laptev, I.; Perez, P.: View-independent action recognition from temporal self-similarities. IEEE Transact. Pattern Anal. Mach. Intell., 33 (2011), 172185.
[9]He, Y.; Le Chevalier, F.; Yarovoy, A.G.: Association of range-doppler video sequences in multistatic UWB radar for human tracking, in European Radar Conf., Netherlands, 2012.
[10]Van Dorp, P.; Groen, F.C.A.: Human walking estimation with radar. IEE Proc. Radar, Sonar Navig., 150 (2003), 356365.
[11]Motion capture database.
[12]Eckmann, J.P.; Kamphorst, S.O.; Ruelle, D.: Recurrence plots of dynamical systems. Europhys. Lett., 4 (1987), 973977.
[13]Cutler, R.; Davis, L.: Robust real-time periodic motion detection, analysis, and applications. IEEE Transact. Pattern Anal. Mach. Intell., 22 (2000), 781796.
[14]Shechtman, E.; Irani, M.: Matching local self-similarities across images and videos, in IEEE Conf. Computer Vision and Pattern Recognition, USA, 2007.
[15]Van der Weken, D.; Nachtegael, M.; Kerre, E.E.: An overview of similarity measures for images, in IEEE Int. Conf. Acoustics, Speech, and Signal Processing, USA, 2002, 3317–3320.
[16]Pluim, J.P.W.; Maintz, J.B.A.; Viergever, M.A.: Mutual-information-based registration of medical images: a survey. IEEE Transact. Med. Imaging, 22 (2003), 9861004.
[17]Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J., 27 (1948), 379423.
[18]Li, J.: Automatic Classification of Human Motions using Doppler Radar. Master thesis, School of Electrical, Computer, and Telecommunications Engineering, University of Wollongong, 2012.
[19]Molchanov, P.O.; Astola, J.T.; Egiazarian, K.O.; Totsky, A.V.: Target classification by using pattern features extracted from bispectrum-based radar Doppler signatures, in Int. Radar Symp., Germany, 2011.
[20]He, Y.; Savelyev, T.G.; Yarovoy, A.G.: Two-stage algorithm for extended target tracking by multistatic UWB radar. IEEE CIE Int. Conf. Radar, China, 2011.


Self-similarity matrix based slow-time feature extraction for human target in high-resolution radar

  • Yuan He (a1), Pascal Aubry (a1), Francois Le Chevalier (a1) and Alexander Yarovoy (a1)


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed