DocumentCode :
2958983
Title :
An intelligent through-the-wall recognition system for homeland security
Author :
Liu, Xiaxiang ; Leung, Henry ; Lampropoulous, George A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Calgary, Calgary, AB
fYear :
2008
fDate :
1-8 June 2008
Firstpage :
2084
Lastpage :
2090
Abstract :
The increasing demands for homeland security boost the development of an intelligent recognition system for through-the-wall sensing. A novel intelligent through-the-wall life recognition engine based on support vector machine (SVM) is provided herein. In this system, micro-Doppler signatures detected from through-the-wall radar are extracted and fed into a SVM classifier. Micro-Doppler effect has great potential for life recognition of human activities, nonhuman but vital subjects, and lifeless targets. Due to time-varying non-stationary characteristic of micro-Doppler feature and its high dimensionality, the SVM classifier is found effective in achieving both computation efficiency and accuracy for this application. Simulation results show that high classification performance is achieved using the proposed recognition system.
Keywords :
Doppler radar; national security; object recognition; radar target recognition; support vector machines; SVM; homeland security; human activities life recognition; intelligent through-the-wall recognition system; microDoppler signatures; support vector machine; through-the-wall radar; through-the-wall sensing; time-varying nonstationary characteristic; Computational modeling; Engines; Humans; Intelligent systems; Machine intelligence; Radar detection; Support vector machine classification; Support vector machines; Target recognition; Terrorism;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location :
Hong Kong
ISSN :
1098-7576
Print_ISBN :
978-1-4244-1820-6
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2008.4634084
Filename :
4634084
Link To Document :
بازگشت