Abstract Different human activity classification based on 3 dimension shape of micro-Doppler signatures is studied. The 3D shape information, including time, frequency and power, is achieved by short-time Fourier transform to Doppler to obtain human pose and motion. The algorithm of point description image is used for obtaining the 3D shape characteristic. The data of 4 motions of 20 people are measured by Doppler radar. The action characteristics are learned by SVM with conformal transforming hyperkernel functions. Then the decision tree model is used for action classification. The improved of kernel functions is studied. The proposed human activity classification and the improved kernel functions are validated by experiments.
[1] Lin A,Ling Hao.A Doppler and Direction-of-Arrival (DDOA) Radar for Multiple-Mover Sensing Based on a Two-Element Array.IEEE Trans on Aerospace Electronic System,2007,43(4): 1496-1509 [2] Thayaparan T,Abrol S,Riseborough E,et al.Analysis of Radar Micro-Doppler Signatures from Experimental Helicopter and Human Data.IET Radar,Sonar and Navigation,2007,1(4): 289-299 [3] Anderson M G,Roger R L.Micro-Doppler Analysis of Multiple Frequency Continuous Wave Radar Signatures.Proc of the SPIE,2007,6547: 65470A [4] Otero M.Application of a Continuous Wave Radar for Human Gait Recognition.Proc of the SPIE,2005,5809: 538–548 [5] Stove A G,Sykes S R.A Doppler-Based Automatic Target Classifier for a Battlefield Surveillance Radar // Proc of the IEEE Radar Conference.Edinburgh,UK,2002: 419-423 [6] Kim Y,Ling Hao.Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine.IEEE Trans on Geoscience and Remote Sensing,2009,47(5): 1328-1337 [7] Zhang Yi,Zhu Yupeng,Cheng Yongqiang,et al.Human Target Radar Echo Signal Analysis Based on Micro-Doppler Characteristic.Signal Processing,2009,25(10): 1616-1623 (in Chinese) (张 翼,朱玉鹏,程永强,等.基于微多普勒特征的人体目标雷达回波信号分析.信号处理,2009,25(10): 1616-1623) [8] Shen Guangping,Wu Haishan.3D Shape Retrieval Algorithm Based on Point Description Image.Computer Engineering,2010,36(4): 286-288 (in Chinese) (沈光平,吴海山.基于点描述图像的三维形状检索算法.计算机工程,2010,36(4): 286-288) [9] Ramon M M,Nan Xu,Christodoulou C G.Beamforming Using Support Vector Machines.IEEE Antennas and Wireless Propagation Letters,2005,4(1): 439-442 [10] Ramon M M,Rojo-Alvarez J L,Camps-Valls G,et al.Kernel Antenna Array Processing.IEEE Trans on Antennas and Propagation,2007,55(3): 642-650 [11] Hon K K B,Zeiner J.Knowledge Brokering for Assisting the Generation of Automotive Product Design.CIRP Annals: Manufacturing Technology,2004,53(1): 159-162 [12] Wu Si,Amari S I.Conformal Transformation of Kernel Functions: A Data-Dependent Way to Improve Support Vector Machine Classifiers.Neural Processing Letters,2002,15(1): 59-67 [13] Wang Hongqiao,Sun Fuchun,Cai Yanning,et al.On Multiple Kernel Learning Methods.Acta Automatica Sinica,2010,36(8): 1037-1050 (in Chinese) (汪洪桥,孙富春,蔡艳宁,等.多核学习方法.自动化学报,2010,36(8): 1037-1050) [14] Xiong Huilin,Zhang Ya,Chen Xuewen.Data-Dependent Kernel Machines for Microarray Data Classification.IEEE/ACM Trans on Computational Biology and Bioinformatics,2007,4(4): 583-595
2012, Vol. 25 
