Human gait recognition using micro-doppler features

The motion of the human limbs results in the unique micro Doppler features which can be used for classification and recognition of different gaits. In this paper, a general human model, together with motion capture data of human motion, is displayed to calculate the expected radar echo and spectrogram of the target. Then the echoes of human torso and limbs are separated based on Chirplet signal representation. The cadence of human motion is extracted from the echo of the limbs to classify the different human gaits. Finally the validity of this feature is verified by computer simulation.

[1]  Eugene F. Greneker,et al.  High-resolution Doppler model of the human gait , 2002, SPIE Defense + Commercial Sensing.

[2]  Hao Ling,et al.  Application of adaptive chirplet representation for ISAR feature extraction from targets with rotating parts , 2003 .

[3]  Tianjian Ji,et al.  Frequency and velocity of walking people , 2005 .

[4]  Tianjian Ji,et al.  FREQUENCY AND VELOCITY OF PEOPLE WALKING , 2005 .

[5]  H. Wechsler,et al.  Micro-Doppler effect in radar: phenomenon, model, and simulation study , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Douglas B. Williams,et al.  Detection and identification of human targets in radar data , 2007, SPIE Defense + Commercial Sensing.

[7]  Hao Ling,et al.  Simulation of human microDopplers using computer animation data , 2008, 2008 IEEE Radar Conference.

[8]  Fredrik Gustafsson,et al.  Human gait parameter estimation based on micro-doppler signatures using particle filters , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).