Classification of micro-Doppler signatures of human aquatic activity through simulation and measurement using transferred learning

Remote detection of human aquatic activity can be applied not only to ocean surveillance but also to rescue operations. When a human is illuminated by electromagnetic waves, a Doppler signal is generated from his or her moving parts. Indeed, bodily movements are what make humans’ micro-Doppler signatures unique, offering a chance to classify human motions. Certain studies have analyzed and attempted to recognize human aquatic activity, but the topic has yet to be extensively studied. In the present research, we simulate the micro-Doppler signatures of a swimming person in an attempt to investigate those signatures’ characteristics. We model human arms as point scatterers while assuming a simple arm motion. By means of such a simulation, we can obtain spectrograms from a swimming person, then extend our measurement to multiple participants. Measurements are taken from five aquatic activities featuring five participants, comprising freestyle, backstroke, and breaststroke, pulling a boat, and rowing. As suggested by the simulation study, the spectrograms for the five activities show different micro-Doppler signatures; hence, we propose to classify them using a deep convolutional neural network (DCNN). In particular, we suggest the use of a transfer-learned DCNN, which is based on a DCNN pretrained by a large-scale RGB image dataset that is, ImageNet. The classification accuracy is calculated using fivefold cross-validation on our dataset. We find that a DCNN trained through transfer learning achieves the highest accuracy while also providing a significant performance boost over the conventional classification method.

[1]  Eugene F. Greneker,et al.  RADAR flashlight for through-the-wall detection of humans , 1998, Defense, Security, and Sensing.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  L. M. Frazier MDR for law enforcement [motion detector radar] , 1998 .

[4]  Youngwook Kim,et al.  Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Uwe Stilla,et al.  Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[6]  Jaakko Astola,et al.  Classification of ground moving targets using bicepstrum-based features extracted from Micro-Doppler radar signatures , 2013, EURASIP Journal on Advances in Signal Processing.

[7]  Keshab K. Parhi,et al.  Semiblind frequency-domain timing synchronization and channel estimation for OFDM systems , 2013, EURASIP J. Adv. Signal Process..

[8]  Ram M. Narayanan,et al.  Classification of human motions using empirical mode decomposition of human micro-Doppler signatures , 2014 .

[9]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[10]  Igal Bilik,et al.  Minimum Divergence Approaches for Robust Classification of Ground Moving Targets , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[11]  F. Groen,et al.  Human walking estimation with radar , 2003 .

[12]  Youngwook Kim,et al.  Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[13]  Carmine Clemente,et al.  A novel algorithm for radar classification based on doppler characteristics exploiting orthogonal Pseudo-Zernike polynomials , 2015, IEEE Transactions on Aerospace and Electronic Systems.

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Trevor Darrell,et al.  Recognizing Image Style , 2013, BMVC.

[16]  Youngwook Kim,et al.  Application of Linear Predictive Coding for Human Activity Classification Based on Micro-Doppler Signatures , 2014, IEEE Geoscience and Remote Sensing Letters.

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